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

    Neuronpedia

    INDEX
    Explanations

    API-related instructions and code snippets

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    iferation
    -0.72
    heid
    -0.70
    arist
    -0.64
    rehens
    -0.61
     Fug
    -0.60
    urity
    -0.60
    ancies
    -0.59
    orsi
    -0.59
     Borders
    -0.59
     acquitted
    -0.58
    POSITIVE LOGITS
     messages
    0.80
    imental
    0.79
     invitations
    0.72
     SMS
    0.71
     notifications
    0.69
    message
    0.69
     "{
    0.68
     notification
    0.68
    itionally
    0.68
    soever
    0.67
    Act Density 12.580%

    No Known Activations