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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and syntax patterns

    oai_token-act-pair · gpt-3.5-turbo

    structured mathematical expressions or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Americ
    -0.77
     antitrust
    -0.74
    76561
    -0.74
    aldi
    -0.73
     newsp
    -0.72
    uese
    -0.69
    atel
    -0.66
    IPS
    -0.65
    ModLoader
    -0.65
     mids
    -0.65
    POSITIVE LOGITS
    âĪĴ
    1.00
     [(
    0.95
     âĪĴ
    0.95
     âĪ
    0.88
     {\
    0.88
    cycle
    0.85
     ',
    0.85
    γ
    0.84
    λ
    0.83
     theorem
    0.81
    Act Density 0.146%

    No Known Activations