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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to making selections or classifications based on defined criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekk
    -0.15
    ebek
    -0.15
    iyan
    -0.15
    ICI
    -0.14
     enim
    -0.14
    dbl
    -0.13
    berman
    -0.13
    ków
    -0.13
    attery
    -0.13
     olmak
    -0.13
    POSITIVE LOGITS
     based
    0.84
     according
    0.80
     Based
    0.69
    according
    0.68
    based
    0.67
    Based
    0.62
    æł¹æį®
    0.61
     According
    0.59
     depending
    0.56
    According
    0.54
    Act Density 0.476%

    No Known Activations