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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to definitions and the act of defining concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inas
    -0.18
    ffects
    -0.15
    675
    -0.15
    fare
    -0.14
    pon
    -0.14
    onto
    -0.14
    465
    -0.14
    ç«ĭãģ¦
    -0.14
    idge
    -0.14
    eros
    -0.14
    POSITIVE LOGITS
    undef
    0.16
     Wolfe
    0.16
    odash
    0.15
     undef
    0.15
    quette
    0.15
     Setter
    0.15
    AVOR
    0.14
    resher
    0.14
    ource
    0.14
    eparator
    0.13
    Act Density 0.067%

    No Known Activations