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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "go" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ję
    -0.74
    ként
    -0.72
     Teich
    -0.71
    minyak
    -0.70
     myst
    -0.70
     Terrasse
    -0.69
    fficiency
    -0.67
     auxili
    -0.65
     Majefty
    -0.64
    auté
    -0.63
    POSITIVE LOGITS
     go
    1.53
     goes
    1.34
    Goes
    1.33
     going
    1.29
     Goes
    1.28
    Go
    1.26
     Go
    1.25
     goin
    1.24
     GO
    1.23
     went
    1.22
    Act Density 0.114%

    No Known Activations