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

    Neuronpedia

    INDEX
    Explanations

    phrases related to beginnings or initiating actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ths
    -0.16
    upon
    -0.15
    enne
    -0.15
    oice
    -0.14
    -strokes
    -0.14
    DAQ
    -0.14
    earch
    -0.14
    ейÑģÑĤв
    -0.14
    .Link
    -0.14
     Bris
    -0.14
    POSITIVE LOGITS
    start
    0.28
    boxing
    0.27
     kicked
    0.25
    -start
    0.24
    starter
    0.24
     Kick
    0.24
    started
    0.24
     kick
    0.23
    kick
    0.22
    Kick
    0.22
    Act Density 0.010%

    No Known Activations