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

    Neuronpedia

    INDEX
    Explanations

    phrases related to starting or initiating actions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kaynak
    -0.16
    azen
    -0.15
    /Typography
    -0.14
    Ñĸдно
    -0.14
    hed
    -0.14
    atz
    -0.14
    imers
    -0.14
    alon
    -0.14
    ufen
    -0.14
    iyon
    -0.13
    POSITIVE LOGITS
    start
    0.31
    boxing
    0.30
    starter
    0.30
     ass
    0.29
    ass
    0.28
    started
    0.28
    -start
    0.27
     butt
    0.27
     off
    0.26
    -off
    0.26
    Act Density 0.010%

    No Known Activations