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

    Neuronpedia

    INDEX
    Explanations

    uppercase acronyms

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to organizations and governmental bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pound
    -0.80
     Conrad
    -0.78
     Franks
    -0.76
     NATO
    -0.75
     Philips
    -0.72
     Sloven
    -0.71
     Merc
    -0.71
     Kickstarter
    -0.71
     Takeru
    -0.71
    alter
    -0.69
    POSITIVE LOGITS
    CLE
    1.03
    ROR
    0.94
    WIN
    0.91
    IR
    0.91
     destro
    0.90
    rha
    0.88
    vana
    0.86
     cumbers
    0.84
    cles
    0.83
    COLOR
    0.83
    Act Density 0.005%

    No Known Activations