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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "to" followed by numbers or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    crap
    -0.16
    iceps
    -0.16
    etros
    -0.16
    allet
    -0.16
    ľ
    -0.15
    urovision
    -0.15
    ë§Ŀ
    -0.15
    ursion
    -0.15
    tribution
    -0.14
    alist
    -0.14
    POSITIVE LOGITS
    ød
    0.16
    034
    0.14
     Tween
    0.14
     Flo
    0.14
     ово
    0.14
    iken
    0.14
     compete
    0.14
    holm
    0.13
    ouched
    0.13
     counter
    0.13
    Act Density 0.072%

    No Known Activations