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

    Neuronpedia

    INDEX
    Explanations

    words related to the severity or importance of a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to varying degrees of severity or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.76
    UME
    -0.74
    ften
    -0.73
    ocene
    -0.73
    ifice
    -0.72
    ilk
    -0.72
    ramid
    -0.71
    ulhu
    -0.70
    naire
    -0.69
    claimer
    -0.69
    POSITIVE LOGITS
     amounts
    1.31
     quantities
    1.05
     doses
    1.02
     levels
    0.95
     proportions
    0.89
     opportunities
    0.88
     credibility
    0.86
     scrutiny
    0.84
     kinds
    0.84
     insights
    0.83
    Act Density 0.375%

    No Known Activations