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

    Neuronpedia

    INDEX
    Explanations

    references to actions or processes involving "to" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DebuggerStep
    -0.56
    ograma
    -0.55
    phrine
    -0.55
    onuclear
    -0.53
    越大
    -0.51
     Vedi
    -0.51
    emde
    -0.50
     regard
    -0.49
    AnchorStyles
    -0.48
    vericks
    -0.48
    POSITIVE LOGITS
     Toh
    0.81
    TO
    0.79
     toc
    0.78
    To
    0.77
     utafitiHapana
    0.74
     Tof
    0.73
     TOS
    0.71
     To
    0.71
     Toe
    0.70
     Tole
    0.69
    Act Density 0.208%

    No Known Activations