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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate temporal progression or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.07
    #
    -0.07
    _marshall
    -0.07
    stag
    -0.07
    eres
    -0.06
     Alarm
    -0.06
    jab
    -0.06
    odu
    -0.06
    ican
    -0.06
    аниÑĨ
    -0.06
    POSITIVE LOGITS
    -
    0.07
    -in
    0.07
    iphery
    0.07
    iglia
    0.07
    ennon
    0.07
    ather
    0.07
    umbnail
    0.06
    inue
    0.06
    ottage
    0.06
    \_
    0.06
    Act Density 0.061%

    No Known Activations