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

    Neuronpedia

    INDEX
    Explanations

    words related to violence or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "ax" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perature
    -0.66
     Shades
    -0.66
    isSpecialOrderable
    -0.64
     finalists
    -0.64
    âĺħâĺħ
    -0.61
    ETHOD
    -0.60
    ishable
    -0.60
     FI
    -0.59
    ochet
    -0.58
     ja
    -0.57
    POSITIVE LOGITS
    xon
    1.17
    xus
    1.09
    illary
    0.99
    seed
    0.98
    es
    0.98
    endale
    0.96
    avier
    0.93
    xes
    0.90
    ercise
    0.89
    iao
    0.89
    Act Density 0.018%

    No Known Activations