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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ję
    -0.68
     Dres
    -0.65
     presence
    -0.63
    fficiency
    -0.62
    misu
    -0.62
     Соб
    -0.61
     Trimble
    -0.61
    teile
    -0.60
     verkrij
    -0.60
     Dud
    -0.60
    POSITIVE LOGITS
     go
    1.10
    Goes
    1.08
     GenerationType
    0.99
     goin
    0.96
    Go
    0.96
     goes
    0.93
    go
    0.93
    Went
    0.93
     Wentworth
    0.89
     Goes
    0.89
    Act Density 0.143%

    No Known Activations