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

    Neuronpedia

    INDEX
    Explanations

    website policies and agreements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to privacy policies and user agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.77
    worth
    -0.68
    Gil
    -0.65
    hall
    -0.65
    hiba
    -0.65
    ãĤ·
    -0.64
    arters
    -0.64
    arson
    -0.64
     Peaks
    -0.63
    tops
    -0.63
    POSITIVE LOGITS
     disclaimer
    1.15
     disclaim
    1.04
     Compliance
    0.99
    claimer
    0.96
     FAQ
    0.88
     confidentiality
    0.86
    anty
    0.83
     waiver
    0.80
     forbids
    0.80
     Policies
    0.80
    Act Density 0.117%

    No Known Activations