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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant quantities or large-scale actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeper
    -0.17
    assen
    -0.15
    аÑģ
    -0.15
    åľŁ
    -0.15
    atk
    -0.15
    zas
    -0.15
    akh
    -0.14
    ahlen
    -0.14
    UED
    -0.14
    _PLACE
    -0.14
    POSITIVE LOGITS
    essional
    0.15
    ez
    0.15
     stand
    0.15
    assis
    0.14
    washer
    0.14
     fora
    0.14
    ession
    0.14
    ipple
    0.14
    hir
    0.13
     Gardner
    0.13
    Act Density 0.026%

    No Known Activations