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

    Neuronpedia

    INDEX
    Explanations

    hyphenated phrases describing groups of people or objects

    oai_token-act-pair · gpt-3.5-turbo

    the double dash punctuation "--"

    oai_token-act-pair · gpt-4-turbo

    hyphens or dashes used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     protective
    -0.74
     discern
    -0.71
    uers
    -0.68
     grave
    -0.68
    othes
    -0.67
     precaution
    -0.65
    ously
    -0.64
     womb
    -0.64
     iceberg
    -0.63
     heart
    -0.63
    POSITIVE LOGITS
    lance
    0.95
    jobs
    0.91
    fuck
    0.91
    _-
    0.88
    something
    0.84
    release
    0.84
    slave
    0.82
    submit
    0.82
    [[
    0.82
    micro
    0.82
    Act Density 0.011%

    No Known Activations