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

    Neuronpedia

    INDEX
    Explanations

    instructions or guides for performing various tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate instructional content or guides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    comments
    -0.82
    ylum
    -0.74
    lights
    -0.73
     Coff
    -0.69
     implication
    -0.68
     promises
    -0.68
    urance
    -0.65
    Statement
    -0.64
    ynes
    -0.63
    enance
    -0.63
    POSITIVE LOGITS
     navigate
    1.11
     maximize
    1.09
     prepare
    1.08
     avoid
    1.06
     customize
    1.06
     emulate
    1.02
     overcome
    1.02
     achieve
    1.01
     learn
    1.01
     organize
    0.99
    Act Density 0.175%

    No Known Activations