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

    Neuronpedia

    INDEX
    Explanations

    references to the English language and related subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellungen
    -0.16
    ally
    -0.15
    506
    -0.15
    tog
    -0.14
     Russo
    -0.14
    eam
    -0.14
    _engine
    -0.14
    ekler
    -0.14
    iciel
    -0.14
    475
    -0.14
    POSITIVE LOGITS
    man
    0.24
    men
    0.22
    woman
    0.21
    enment
    0.21
    -speaking
    0.20
    ment
    0.19
    women
    0.19
    mann
    0.18
    erman
    0.18
    meni
    0.17
    Act Density 0.022%

    No Known Activations