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

    Neuronpedia

    INDEX
    Explanations

    statements addressing the reader directly about their actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ´»
    -0.18
     Bec
    -0.17
    urdy
    -0.15
    DATE
    -0.14
    bec
    -0.14
    aines
    -0.14
     Bien
    -0.14
     becoming
    -0.14
    /goto
    -0.13
    prene
    -0.13
    POSITIVE LOGITS
     encounter
    0.22
     experience
    0.22
    _experience
    0.18
    RIX
    0.18
     experiences
    0.18
     encounters
    0.18
    experience
    0.18
     experiencing
    0.17
     Experience
    0.17
     encountering
    0.17
    Act Density 0.161%

    No Known Activations