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

    Neuronpedia

    INDEX
    Explanations

    words related to a question or uncertainty, particularly with a focus on financial or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "HILL" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Star
    -0.64
     Static
    -0.64
     Sty
    -0.63
     sight
    -0.63
     sibling
    -0.62
     bro
    -0.61
     Pod
    -0.60
     soc
    -0.60
     Wo
    -0.58
     zo
    -0.58
    POSITIVE LOGITS
    ILL
    4.21
    illing
    2.06
    illed
    2.03
    ills
    2.02
    ill
    1.97
    iller
    1.85
    ILLE
    1.79
    IL
    1.41
    ULL
    1.37
    illa
    1.34
    Act Density 0.009%

    No Known Activations