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

    Neuronpedia

    INDEX
    Explanations

    words related to sending direct messages (DMs) or similar communication methods

    oai_token-act-pair · gpt-3.5-turbo

    references to "DM" (Digital Millennium) related terms or abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.69
    lihood
    -0.68
     Laur
    -0.66
    bury
    -0.66
    Magikarp
    -0.65
    gio
    -0.64
    bite
    -0.63
     Emirates
    -0.63
    ÃįÃį
    -0.63
    lies
    -0.63
    POSITIVE LOGITS
    NF
    1.03
    ETHOD
    0.85
    NM
    0.83
    DM
    0.82
    emonic
    0.81
    ARC
    0.79
    NT
    0.77
    ERG
    0.77
    MC
    0.76
    ND
    0.76
    Act Density 0.015%

    No Known Activations