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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "go" or its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auté
    -0.72
    DateTimeField
    -0.68
     balancer
    -0.64
     précie
    -0.63
     mergeFrom
    -0.63
     Municipalidad
    -0.62
     élect
    -0.60
    piew
    -0.60
     Dès
    -0.59
     fört
    -0.59
    POSITIVE LOGITS
     go
    0.90
     going
    0.86
    Went
    0.85
     went
    0.81
     gone
    0.79
     Audiodateien
    0.78
     Going
    0.78
    Going
    0.77
     travelling
    0.76
     goin
    0.74
    Act Density 0.091%

    No Known Activations