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

    Neuronpedia

    INDEX
    Explanations

    verbs that express movement or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ję
    -0.77
    ként
    -0.75
     myst
    -0.73
    minyak
    -0.73
     Teich
    -0.73
     Terrasse
    -0.70
     Huddersfield
    -0.68
     Majefty
    -0.68
     purpoſe
    -0.67
     tarvit
    -0.66
    POSITIVE LOGITS
     go
    1.47
     going
    1.39
     goes
    1.34
    Goes
    1.33
     goin
    1.29
     Goes
    1.27
     went
    1.26
    Going
    1.25
     Going
    1.24
    Went
    1.22
    Act Density 0.124%

    No Known Activations