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

    Neuronpedia

    INDEX
    Explanations

    words related to initiating actions or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to beginnings and initiations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.92
       
    -0.87
     Kassel
    -0.86
     Redmi
    -0.86
     Plume
    -0.86
     contextLoads
    -0.85
     Coliseum
    -0.84
    -0.84
    Viki
    -0.82
    CrossRef
    -0.81
    POSITIVE LOGITS
     start
    1.43
    START
    1.40
     Start
    1.39
     Starts
    1.39
     START
    1.38
     starts
    1.38
    starts
    1.32
    Start
    1.29
     started
    1.27
    start
    1.25
    Act Density 0.097%

    No Known Activations