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

    Neuronpedia

    INDEX
    Explanations

    verbs associated with initiation or beginnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kassel
    -0.83
       
    -0.81
     Coliseum
    -0.81
    KommentareTeilen
    -0.78
     Poliz
    -0.77
     Plume
    -0.76
    Nonnull
    -0.76
     Redmi
    -0.76
    }\]
    -0.75
     MIMO
    -0.75
    POSITIVE LOGITS
     start
    1.49
     starts
    1.48
    START
    1.46
     START
    1.46
     Starts
    1.45
    starts
    1.44
     Start
    1.43
    Start
    1.34
    start
    1.32
    Starts
    1.32
    Act Density 0.114%

    No Known Activations