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

    Neuronpedia

    INDEX
    Explanations

    references to "cool" or similarly appreciated qualities and positive sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phant
    -0.17
    åĵģ
    -0.16
    oder
    -0.15
    .Encoding
    -0.14
    lar
    -0.14
    éij
    -0.14
    bai
    -0.14
    ç°
    -0.14
    ucci
    -0.14
    _nr
    -0.13
    POSITIVE LOGITS
    éal
    0.16
    avad
    0.15
    .Fat
    0.15
    ë§Ŀ
    0.15
    اشت
    0.15
    Scaler
    0.15
    aged
    0.15
    \Redirect
    0.14
    isos
    0.14
    彡
    0.14
    Act Density 0.268%

    No Known Activations