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

    Neuronpedia

    INDEX
    Explanations

    phrases within quotations to express strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    quoted statements expressing strong emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.71
    omorphic
    -0.70
    icular
    -0.70
    paren
    -0.67
    Ļ½
    -0.67
    stant
    -0.67
    ulic
    -0.66
    ackets
    -0.66
    elta
    -0.65
    ¾
    -0.64
    POSITIVE LOGITS
    /"
    0.92
    alos
    0.65
    >>\
    0.64
     Griff
    0.63
     AAP
    0.62
     remark
    0.60
     revealing
    0.60
    ãģ®ç
    0.59
     recommending
    0.59
    sic
    0.58
    Act Density 0.075%

    No Known Activations