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

    Neuronpedia

    INDEX
    Explanations

    references to the word "abyss" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndra
    -0.74
    yright
    -0.73
    etary
    -0.71
    agers
    -0.67
    pton
    -0.66
     Gohan
    -0.66
    hood
    -0.64
    åĤ
    -0.63
    STON
    -0.63
    ciation
    -0.61
    POSITIVE LOGITS
    inia
    1.23
    inian
    1.17
     Dwell
    1.02
    omorph
    0.82
    ologist
    0.82
    door
    0.81
    rane
    0.79
    alon
    0.78
    urous
    0.77
    lain
    0.74
    Act Density 0.042%

    No Known Activations