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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "going."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Alcott
    -0.87
     TestBed
    -0.84
     NSS
    -0.82
     HasFactory
    -0.82
    rsiniz
    -0.81
    yym
    -0.77
     समीक्षक
    -0.77
     tartalomajánló
    -0.77
     PSM
    -0.72
     parseFrom
    -0.71
    POSITIVE LOGITS
    tableFuture
    0.85
     Gonna
    0.71
     gonna
    0.70
     want
    0.68
     konst
    0.66
     GONNA
    0.66
     supposed
    0.65
     angeb
    0.63
    要
    0.63
     going
    0.60
    Act Density 0.016%

    No Known Activations