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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or subjective interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CONSIN
    -0.63
    Aholisi
    -0.59
     referenties
    -0.59
     BoxDecoration
    -0.57
    akaran
    -0.56
    trong
    -0.54
     Aussch
    -0.53
     sério
    -0.51
    ruitment
    -0.51
     Treff
    -0.51
    POSITIVE LOGITS
     Autorizaciones
    0.68
    GetAxis
    0.68
    timate
    0.67
     nice
    0.60
    coroutines
    0.59
     SANTA
    0.58
    bufio
    0.57
     Angew
    0.57
    Cheque
    0.56
    ỏi
    0.56
    Act Density 0.078%

    No Known Activations