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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs related to interactions and relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Embeddable
    -0.52
    ModelMap
    -0.44
    getFloat
    -0.42
    Holstein
    -0.41
    Maestro
    -0.41
    CultureInfo
    -0.40
     dépens
    -0.40
    Explor
    -0.40
    RequestMethod
    -0.39
    getActivity
    -0.39
    POSITIVE LOGITS
     jetta
    0.78
     chrysler
    0.77
     shayari
    0.74
     mondeo
    0.72
     pajero
    0.69
     voleva
    0.66
     regardant
    0.65
     camry
    0.64
     scrat
    0.64
     hilux
    0.63
    Act Density 0.218%

    No Known Activations