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

    Neuronpedia

    INDEX
    Explanations

    words related to deep contemplation and introspection

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of "thought."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Adin
    -0.68
    ALL
    -0.67
    ORPG
    -0.67
    BIP
    -0.64
    KY
    -0.63
    anca
    -0.63
    ipher
    -0.62
    conservancy
    -0.62
    inia
    -0.62
     Kats
    -0.61
    POSITIVE LOGITS
    fully
    1.12
    fulness
    1.09
    lessly
    0.95
     provoking
    0.86
    orial
    0.80
    ful
    0.79
    istically
    0.77
    pad
    0.76
    lessness
    0.75
    ileaks
    0.73
    Act Density 0.026%

    No Known Activations