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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udem
    -0.19
    loon
    -0.17
    PRS
    -0.15
    umo
    -0.15
    .Percent
    -0.15
    sez
    -0.15
    ì§ľ
    -0.14
     ì¶ľìŀ¥
    -0.14
    énom
    -0.14
    infeld
    -0.14
    POSITIVE LOGITS
     turnaround
    0.16
     suddenly
    0.16
     opposite
    0.16
    UNKNOWN
    0.16
     TRACE
    0.15
    lac
    0.15
    ,
    0.15
     quick
    0.15
     within
    0.15
    .
    0.14
    Act Density 0.174%

    No Known Activations