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

    Neuronpedia

    INDEX
    Explanations

    expressions related to forceful impact or action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "hit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouver
    -0.78
    pires
    -0.74
    ¥ŀ
    -0.73
     tyrann
    -0.69
     conve
    -0.68
    etheless
    -0.66
     horns
    -0.65
     offic
    -0.64
     displaying
    -0.63
    MpServer
    -0.63
    POSITIVE LOGITS
    hit
    1.16
    achi
    0.93
    oshi
    0.88
    endra
    0.83
    ãĥĥãĤ¯
    0.82
    chens
    0.79
    ched
    0.79
    hog
    0.78
    enson
    0.76
    ingly
    0.76
    Act Density 0.011%

    No Known Activations