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

    Neuronpedia

    INDEX
    Explanations

    words related to existential inquiries or modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reeze
    -0.17
    quine
    -0.16
     Consort
    -0.16
    azers
    -0.15
    pong
    -0.15
    _CS
    -0.15
    Separated
    -0.15
    emale
    -0.14
    uffy
    -0.14
    _CT
    -0.14
    POSITIVE LOGITS
    Bindings
    0.16
    iasm
    0.15
    μεν
    0.14
    unts
    0.14
    asma
    0.14
    amework
    0.14
    Acceler
    0.14
    ãĤ¤ãĥĦ
    0.14
    odos
    0.13
     Ant
    0.13
    Act Density 0.001%

    No Known Activations