Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and evaluations related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "in" or "their" in specific contexts

    np_acts-logits-general · gemini-2.0-flash

    describing experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.79
    enumii
    -0.78
     bezeichneter
    -0.71
    XmlAccessType
    -0.69
    DockStyle
    -0.68
    setAccessible
    -0.66
     insuffisamment
    -0.66
    RefNanny
    -0.64
     AssemblyCompany
    -0.64
    İstinadlar
    -0.63
    POSITIVE LOGITS
     buying
    0.86
     performing
    0.79
     accessing
    0.77
     purchasing
    0.77
     installing
    0.77
     planting
    0.74
     executing
    0.74
     submitting
    0.73
     eating
    0.73
     administering
    0.73
    Act Density 1.076%

    No Known Activations