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

    Neuronpedia

    INDEX
    Explanations

    references to data structures and types in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iais
    -0.19
    amer
    -0.15
     blunt
    -0.14
    lector
    -0.14
    kl
    -0.14
    ardon
    -0.14
    leck
    -0.14
    ager
    -0.13
    ym
    -0.13
    kind
    -0.13
    POSITIVE LOGITS
     whose
    0.41
    whose
    0.33
     deemed
    0.20
     that
    0.19
     who
    0.18
     which
    0.17
     vá»ijn
    0.17
     nÃło
    0.16
     ÏĢοÏħ
    0.16
     where
    0.15
    Act Density 0.411%

    No Known Activations