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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the nature or characteristics of actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to limitations and sporadic issues in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.84
    iage
    -0.82
    orks
    -0.80
    kees
    -0.79
    onica
    -0.77
    kay
    -0.77
    gdala
    -0.76
    raine
    -0.76
    olphins
    -0.75
    deen
    -0.75
    POSITIVE LOGITS
     predictable
    1.12
     riddled
    1.09
     reliant
    1.08
     unpredictable
    1.06
     comprised
    1.02
     fragmented
    1.02
     characterized
    1.01
     dependent
    1.00
     inconsistent
    1.00
     irreversible
    0.98
    Act Density 0.233%

    No Known Activations