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

    Neuronpedia

    INDEX
    Explanations

    concepts related to deep thinking or contemplation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "thought" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARDS
    -0.70
    ALL
    -0.66
    BIP
    -0.66
    lehem
    -0.64
     Peninsula
    -0.64
    Availability
    -0.63
    ards
    -0.63
    anca
    -0.61
     toe
    -0.60
     Tens
    -0.58
    POSITIVE LOGITS
    fulness
    1.26
    fully
    1.20
     provoking
    1.15
    lessly
    1.15
    lessness
    0.95
    less
    0.85
    orial
    0.82
    borgh
    0.81
    sworth
    0.81
    ful
    0.79
    Act Density 0.032%

    No Known Activations