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

    Neuronpedia

    INDEX
    Explanations

    elements related to character development and narrative structure in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ábado
    -0.15
    ertiary
    -0.15
    bourg
    -0.14
    arih
    -0.14
    eeper
    -0.14
    agma
    -0.13
    æŃ
    -0.13
    åł¡
    -0.13
    unic
    -0.13
    amedi
    -0.13
    POSITIVE LOGITS
     remains
    0.35
     still
    0.34
     later
    0.32
     eventually
    0.29
     remain
    0.29
    still
    0.28
     forever
    0.27
    later
    0.27
    bec
    0.26
     eventual
    0.26
    Act Density 0.320%

    No Known Activations