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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong opinions or directives

    oai_token-act-pair · gpt-3.5-turbo

    urgent requests or pleas for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MpServer
    -0.77
     tender
    -0.63
     eff
    -0.62
     ribbon
    -0.62
     counterparts
    -0.62
     bitters
    -0.61
     chunks
    -0.59
     tang
    -0.59
    ¯¯¯¯¯¯¯¯
    -0.58
     Victory
    -0.57
    POSITIVE LOGITS
    amac
    0.80
    ultural
    0.77
    ylum
    0.75
    ULT
    0.73
    reditary
    0.72
    ahar
    0.69
    sonian
    0.68
    amina
    0.68
    ultan
    0.67
    lest
    0.67
    Act Density 0.000%

    No Known Activations