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

    Neuronpedia

    INDEX
    Explanations

    repeated or hedged phrases and variations indicating uncertainty or approximation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.81
     charité
    -0.70
     OMITBAD
    -0.67
    zzar
    -0.66
     nakalista
    -0.65
    Tikang
    -0.62
    ⓧ
    -0.62
    Становништво
    -0.62
     Autorizaciones
    -0.61
     RSSSF
    -0.61
    POSITIVE LOGITS
    Su
    0.82
     su
    0.76
     Su
    0.76
    su
    0.76
    SO
    0.75
    SU
    0.72
    si
    0.72
     sa
    0.72
    SI
    0.70
     SY
    0.69
    Act Density 0.227%

    No Known Activations