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

    Neuronpedia

    INDEX
    Explanations

    phrases related to silencing or stopping something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to silencing or shutting down

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APH
    -0.72
     likeness
    -0.69
    pain
    -0.69
     sophistication
    -0.68
    KNOWN
    -0.67
    apego
    -0.66
    nard
    -0.66
    ammy
    -0.64
     maturity
    -0.64
    VL
    -0.64
    POSITIVE LOGITS
    byss
    0.76
     Deng
    0.71
    road
    0.64
    sec
    0.61
    anded
    0.61
    Repeat
    0.61
    Ped
    0.61
    ipedia
    0.60
    baugh
    0.59
    eye
    0.59
    Act Density 0.096%

    No Known Activations