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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating declarations or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acha
    -0.17
    inz
    -0.15
    reet
    -0.15
    ulk
    -0.15
     Warm
    -0.14
    hee
    -0.14
    ia
    -0.13
    º
    -0.13
     sting
    -0.13
    ishop
    -0.13
    POSITIVE LOGITS
    ogui
    0.21
    utor
    0.18
    æľĭ
    0.18
    undef
    0.16
    ellite
    0.16
    ICLE
    0.15
    idak
    0.15
     lại
    0.15
     Unidos
    0.15
    olith
    0.15
    Act Density 0.017%

    No Known Activations