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

    Neuronpedia

    INDEX
    Explanations

    names or mentions of a specific publication

    oai_token-act-pair · gpt-3.5-turbo

    words related to inquiries and demands, particularly in a news or editorial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ijah
    -0.80
     brute
    -0.77
     challeng
    -0.75
     conflic
    -0.73
     stalking
    -0.72
    ajo
    -0.71
     showc
    -0.71
     surv
    -0.71
     lifes
    -0.71
     deliberations
    -0.70
    POSITIVE LOGITS
    ments
    1.10
    ment
    0.96
    rer
    0.95
    teen
    0.93
    rers
    0.91
    mented
    0.89
    TION
    0.87
    MENT
    0.86
    MENTS
    0.84
    ty
    0.80
    Act Density 0.035%

    No Known Activations