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

    Neuronpedia

    INDEX
    Explanations

    tokens and formatting related to mathematical expressions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inclu
    -0.14
    'gc
    -0.14
    lyn
    -0.13
     SOCKET
    -0.13
    iliation
    -0.13
    $MESS
    -0.13
    кÑĥÑĤ
    -0.13
     Hüs
    -0.13
    bung
    -0.13
     Hin
    -0.13
    POSITIVE LOGITS
    inan
    0.15
    aylor
    0.14
     Belt
    0.14
    IQ
    0.14
    OTO
    0.14
    oming
    0.14
    visor
    0.14
    otti
    0.13
     Roosevelt
    0.13
    tas
    0.13
    Act Density 0.235%

    No Known Activations