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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote various types of abilities and capacities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ishly
    -0.18
    ilo
    -0.17
    راÙĨ
    -0.17
    ers
    -0.17
    inee
    -0.16
    rej
    -0.15
    ery
    -0.15
     GRAT
    -0.15
    eters
    -0.15
    Ậ
    -0.15
    POSITIVE LOGITS
    -bodied
    0.30
    /dis
    0.17
     bod
    0.17
    ius
    0.16
    hood
    0.16
    son
    0.16
    unch
    0.16
    ies
    0.16
    uali
    0.16
    ty
    0.15
    Act Density 0.029%

    No Known Activations