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

    Neuronpedia

    INDEX
    Explanations

    phrases related to influence, control, and power dynamics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "of" followed by various nouns or phrases indicating possession or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.98
    quartered
    -0.80
    iste
    -0.73
    minus
    -0.73
    ©¶æ¥µ
    -0.71
    amount
    -0.71
    KA
    -0.70
    nces
    -0.70
    querque
    -0.69
    illac
    -0.69
    POSITIVE LOGITS
     unsuspecting
    0.73
     Gul
    0.72
     Marshal
    0.72
     Randolph
    0.71
     those
    0.71
     whoever
    0.71
     anyone
    0.71
     Dru
    0.69
     Fritz
    0.68
     Satan
    0.67
    Act Density 0.125%

    No Known Activations