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

    Neuronpedia

    INDEX
    Explanations

    words related to military operations and equipment

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate specific conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Citiz
    -0.56
     Byrd
    -0.54
     charism
    -0.54
     Osw
    -0.53
     Fut
    -0.52
     Reich
    -0.52
    public
    -0.51
     unpop
    -0.51
    undai
    -0.50
     trave
    -0.49
    POSITIVE LOGITS
    ioned
    0.80
    enance
    0.74
    LESS
    0.68
    thood
    0.67
    ragon
    0.67
    aneously
    0.65
    illion
    0.64
    SHIP
    0.62
    xual
    0.62
    ciation
    0.61
    Act Density 0.567%

    No Known Activations