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

    Neuronpedia

    INDEX
    Explanations

    names containing the letters "irl"

    oai_token-act-pair · gpt-3.5-turbo

    references to characters or elements within fictional narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.78
    ħĭ
    -0.72
    ector
    -0.61
    QUIRE
    -0.61
    plete
    -0.59
    natal
    -0.59
     calculating
    -0.59
    Progress
    -0.59
     explorer
    -0.58
    PROV
    -0.57
    POSITIVE LOGITS
    ibrary
    0.96
    onge
    0.95
    iffe
    0.93
    itudinal
    0.90
    oons
    0.89
    inations
    0.86
    inders
    0.86
    itude
    0.86
    iffs
    0.85
    abs
    0.84
    Act Density 0.022%

    No Known Activations