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

    Neuronpedia

    INDEX
    Explanations

    numerical values followed by punctuation often found in mathematical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ema
    -0.17
    viÄį
    -0.16
     pacman
    -0.16
     pac
    -0.15
    nze
    -0.15
    ceb
    -0.14
    umba
    -0.14
    بÙĬر
    -0.14
    pac
    -0.14
    ancia
    -0.14
    POSITIVE LOGITS
    izio
    0.17
    arda
    0.15
    weise
    0.14
    atatype
    0.14
    .outputs
    0.14
    imity
    0.14
    Advance
    0.14
    613
    0.13
    ADR
    0.13
    ented
    0.13
    Act Density 0.022%

    No Known Activations