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

    Neuronpedia

    INDEX
    Explanations

    terms related to important concepts or themes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to complex problem-solving and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atorium
    -0.66
    âĸ¬
    -0.64
    ãĤ¨ãĥ«
    -0.61
    Reader
    -0.60
     Tycoon
    -0.58
    REDACTED
    -0.57
     fingerprint
    -0.56
    Charge
    -0.56
    Entry
    -0.55
    same
    -0.54
    POSITIVE LOGITS
    poons
    1.23
    hips
    1.16
    paces
    1.12
    uits
    1.10
    mith
    1.08
    pace
    1.01
    cale
    1.00
    hip
    0.99
    pring
    0.96
    manship
    0.95
    Act Density 0.546%

    No Known Activations