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

    Neuronpedia

    INDEX
    Explanations

    double asterisks '**' in the text

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters used in various contexts, particularly those that represent placeholders or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pel
    -0.64
    ãĤ·ãĥ£
    -0.64
     Federation
    -0.63
     Hein
    -0.61
     Sop
    -0.60
     alert
    -0.59
     surg
    -0.59
     smuggling
    -0.59
    eworld
    -0.59
     federation
    -0.59
    POSITIVE LOGITS
    **
    3.96
     **
    2.80
    ***
    2.35
    ****
    2.07
    *
    2.07
    *****
    1.95
    *,
    1.95
    *.
    1.93
    âĢł
    1.87
    *)
    1.82
    Act Density 0.009%

    No Known Activations