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

    Neuronpedia

    INDEX
    Explanations

    phrases implying a high level of certainty or inevitability

    oai_token-act-pair · gpt-3.5-turbo

    words indicating a high degree of certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eworld
    -0.68
     ASAP
    -0.67
    IFA
    -0.65
     Citation
    -0.65
     DN
    -0.62
     Dod
    -0.62
    RAW
    -0.60
    bright
    -0.59
    poke
    -0.58
     Wonderland
    -0.58
    POSITIVE LOGITS
     populated
    0.67
     torn
    0.66
     wraps
    0.65
    士
    0.64
     skim
    0.63
     sidx
    0.63
    ernel
    0.63
    rontal
    0.63
    ctory
    0.62
    NetMessage
    0.60
    Act Density 0.167%

    No Known Activations