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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or judicial proceedings

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to the word 'murder' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Diaz
    -0.71
    js
    -0.67
    hra
    -0.66
    cia
    -0.62
    ttes
    -0.62
    jc
    -0.62
    cean
    -0.62
    ÄŁ
    -0.62
    cca
    -0.62
    ge
    -0.60
    POSITIVE LOGITS
    ING
    1.61
    NING
    1.53
    NER
    1.43
    EST
    1.39
    LIN
    1.37
    INGS
    1.37
    ER
    1.34
    ILL
    1.34
    ELL
    1.30
    ED
    1.29
    Act Density 0.142%

    No Known Activations