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

    Neuronpedia

    INDEX
    Explanations

    phrases involving directions or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Namib
    -0.60
     Compagn
    -0.57
     Zamb
    -0.56
    herence
    -0.55
     cuban
    -0.55
    oplayer
    -0.55
     Lusaka
    -0.54
     Assad
    -0.53
     incomplète
    -0.52
     kiin
    -0.51
    POSITIVE LOGITS
    goTo
    0.94
    بوابة
    0.88
     goTo
    0.87
     GenerationType
    0.83
    DockStyle
    0.82
    tdessen
    0.80
     consultato
    0.79
    RepeatedField
    0.78
    一起去
    0.78
    goto
    0.78
    Act Density 0.212%

    No Known Activations