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

    Neuronpedia

    INDEX
    Explanations

    the word "Virgin" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Virgin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kson
    -0.86
    pter
    -0.81
    ld
    -0.77
    ggle
    -0.76
    lda
    -0.76
    berman
    -0.73
    plin
    -0.72
    occ
    -0.71
    cki
    -0.70
    govtrack
    -0.69
    POSITIVE LOGITS
     Islands
    1.15
     Galactic
    1.06
    ity
    0.98
    ian
    0.89
     Virgin
    0.86
    ians
    0.85
     pigeon
    0.84
     pige
    0.83
    ius
    0.81
    ias
    0.80
    Act Density 0.061%

    No Known Activations