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

    Neuronpedia

    INDEX
    Explanations

    words related to sparking or inciting action or change

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spur" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.70
    atched
    -0.65
     Patriarch
    -0.63
    arning
    -0.62
    arov
    -0.62
    ĨĴ
    -0.61
     mastering
    -0.60
     Templ
    -0.59
     Warriors
    -0.59
    ynski
    -0.59
    POSITIVE LOGITS
    iously
    0.99
     spur
    0.96
    minist
    0.84
    uitous
    0.79
    whe
    0.79
    ped
    0.79
    PsyNetMessage
    0.78
    ãĥĥ
    0.75
    ãĤ¡
    0.75
    GGGGGGGG
    0.74
    Act Density 0.011%

    No Known Activations