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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of "kicking" or "initiating" actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cronin
    -0.70
    ymce
    -0.70
     Nair
    -0.67
     Meksiku
    -0.66
    θει
    -0.66
    zeitung
    -0.65
     πως
    -0.63
     Payne
    -0.63
    norr
    -0.63
    ilmente
    -0.63
    POSITIVE LOGITS
     kick
    1.78
     Kick
    1.72
     kicked
    1.72
     KICK
    1.72
    kick
    1.61
     kicks
    1.60
    Kick
    1.60
     kicking
    1.52
     Kicks
    1.45
    kicks
    1.34
    Act Density 0.060%

    No Known Activations