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

    Neuronpedia

    INDEX
    Explanations

    the word "Sorcery"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "sorcery" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faults
    -0.75
    ãĥĥãĥĪ
    -0.74
    ansion
    -0.72
    ealous
    -0.70
    ablishment
    -0.68
    oppers
    -0.67
    ocobo
    -0.66
    umbnail
    -0.65
    isodes
    -0.64
     earnest
    -0.63
    POSITIVE LOGITS
    cia
    0.88
    vana
    0.85
    ority
    0.82
    atos
    0.77
    cery
    0.77
    ittal
    0.77
    culus
    0.76
    lich
    0.74
    rha
    0.73
    cules
    0.71
    Act Density 0.043%

    No Known Activations