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

    Neuronpedia

    INDEX
    Explanations

    equals sign assignments in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysz
    -0.16
    bidden
    -0.15
    assy
    -0.14
    udeau
    -0.14
     understanding
    -0.14
     kick
    -0.14
    Codec
    -0.14
    bomb
    -0.14
    jsc
    -0.13
    ly
    -0.13
    POSITIVE LOGITS
     Heller
    0.15
    dorf
    0.14
    _variant
    0.14
    abella
    0.14
     Dit
    0.14
    ħį
    0.13
    iferay
    0.13
    queues
    0.13
    itm
    0.13
    даÑħ
    0.13
    Act Density 0.091%

    No Known Activations