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

    Neuronpedia

    INDEX
    Explanations

    references to specific scenes or settings in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    standing
    -0.17
    deaux
    -0.16
    lander
    -0.15
    inç
    -0.15
    aload
    -0.15
    ters
    -0.15
    udge
    -0.15
    achi
    -0.14
    nger
    -0.14
    kiem
    -0.14
    POSITIVE LOGITS
    uate
    0.17
    ýš
    0.17
    人çī©
    0.15
    rack
    0.15
    ed
    0.15
    Ø©
    0.15
    eker
    0.15
    eg
    0.14
    antro
    0.14
    adan
    0.14
    Act Density 0.038%

    No Known Activations