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

    Neuronpedia

    INDEX
    Explanations

    negative portrayals or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to portrayal, critique, and general analysis of subjects in discussions or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    putable
    -0.60
    zan
    -0.56
     unbeliev
    -0.55
    inyl
    -0.52
    ãĥĥãĥī
    -0.50
    oug
    -0.49
     certific
    -0.49
    OPLE
    -0.48
    IER
    -0.48
    elta
    -0.48
    POSITIVE LOGITS
     of
    1.46
    of
    1.19
     thereof
    1.17
     Of
    1.16
     OF
    1.11
    Of
    1.11
    oft
    0.82
    OF
    0.78
    ta
    0.75
    eatures
    0.70
    Act Density 0.383%

    No Known Activations