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

    Neuronpedia

    INDEX
    Explanations

    expressions of awareness or communication around societal norms and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ«è¦ĭ
    -0.16
    alin
    -0.15
    anners
    -0.15
    elp
    -0.15
    LastError
    -0.15
    ampo
    -0.14
    onet
    -0.14
    (disposing
    -0.14
    SError
    -0.14
    isen
    -0.14
    POSITIVE LOGITS
     told
    0.36
     hearing
    0.27
     hear
    0.27
     heard
    0.26
     hears
    0.24
     receive
    0.23
     Hearing
    0.23
     informed
    0.23
     received
    0.22
     learn
    0.22
    Act Density 0.232%

    No Known Activations