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

    Neuronpedia

    INDEX
    Explanations

    phrases focused on capabilities and skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilo
    -0.17
    Ậ
    -0.17
    ishly
    -0.17
    راÙĨ
    -0.17
    inee
    -0.16
     GRAT
    -0.16
    rej
    -0.15
    ers
    -0.15
    ikal
    -0.15
    eters
    -0.15
    POSITIVE LOGITS
    -bodied
    0.29
    ies
    0.18
    unch
    0.18
    esk
    0.18
    ments
    0.18
    /dis
    0.17
    hood
    0.17
    uali
    0.17
    son
    0.16
    ment
    0.16
    Act Density 0.030%

    No Known Activations