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

    Neuronpedia

    INDEX
    Explanations

    phrases related to responses or reactions to significant events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alternative
    -0.16
    amet
    -0.15
     Wolff
    -0.15
    istr
    -0.14
    496
    -0.14
    Disposed
    -0.14
    ignet
    -0.14
     ill
    -0.14
    uly
    -0.14
    екÑĤ
    -0.14
    POSITIVE LOGITS
    izz
    0.16
     forks
    0.16
    gend
    0.14
    á»ĩn
    0.14
    resher
    0.14
    .ParseException
    0.14
    ebin
    0.13
     fork
    0.13
    ynes
    0.13
    ëħ
    0.13
    Act Density 0.011%

    No Known Activations