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

    Neuronpedia

    INDEX
    Explanations

    terms related to privacy and personal space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £½
    -0.15
    eson
    -0.14
    esses
    -0.14
    ово
    -0.14
    mann
    -0.14
    Invariant
    -0.14
    lassian
    -0.14
    aeda
    -0.13
     Baghd
    -0.13
     planta
    -0.13
    POSITIVE LOGITS
    /private
    0.19
    /conf
    0.18
    олÑı
    0.15
     rein
    0.15
    eer
    0.14
    arrera
    0.14
    ê³
    0.14
     ent
    0.14
     unless
    0.14
    /Public
    0.14
    Act Density 0.032%

    No Known Activations