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

    Neuronpedia

    INDEX
    Explanations

    the word "Pal" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Palmyra" and related geopolitical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.85
    minded
    -0.82
    ICLE
    -0.78
    lessly
    -0.72
    urities
    -0.68
    UNE
    -0.67
    åŃIJ
    -0.64
    aspx
    -0.64
    éĹĺ
    -0.63
    nesses
    -0.63
    POSITIVE LOGITS
    atial
    1.04
    estine
    0.98
    agin
    0.96
    assic
    0.96
    myra
    0.95
    adin
    0.94
    mares
    0.91
    yss
    0.91
    ikan
    0.90
    amic
    0.90
    Act Density 0.006%

    No Known Activations