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

    Neuronpedia

    INDEX
    Explanations

    terms related to cognitive processes and learning dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ©
    -0.18
    otle
    -0.17
    åĹ
    -0.16
    ойно
    -0.16
     Levine
    -0.15
    azor
    -0.14
    ogenerated
    -0.14
    morph
    -0.14
    ábado
    -0.14
    lish
    -0.14
    POSITIVE LOGITS
     Silk
    0.15
    arga
    0.15
     cushions
    0.15
     FileAccess
    0.14
    åį
    0.14
    ково
    0.14
    ì¡°
    0.14
    ukkan
    0.14
    zel
    0.14
    312
    0.14
    Act Density 0.039%

    No Known Activations