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

    Neuronpedia

    INDEX
    Explanations

    phrases related to nominations and applications for awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ki
    -0.16
    allery
    -0.16
    ks
    -0.16
    annis
    -0.15
    anger
    -0.15
     threats
    -0.15
    ath
    -0.15
    ilde
    -0.14
     Gos
    -0.14
    ari
    -0.13
    POSITIVE LOGITS
    ÌĨ
    0.18
    xFD
    0.16
    uss
    0.15
    ect
    0.14
    ı
    0.14
    aeper
    0.14
     collo
    0.13
    raquo
    0.13
    éī
    0.13
    ิà¸ĩ
    0.13
    Act Density 0.041%

    No Known Activations