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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions indicative of equations and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.93
     चीज़ों
    -0.76
    GraphicsUnit
    -0.75
    __(/*!
    -0.74
    ftagPool
    -0.71
     فريبيس
    -0.66
     nahilalakip
    -0.65
    findpost
    -0.63
    hoeddwyd
    -0.62
     utafitiHapana
    -0.60
    POSITIVE LOGITS
     substituting
    0.94
     substitution
    0.79
     Substitution
    0.78
     Substituting
    0.78
    Substituting
    0.77
     plugging
    0.75
    Substitution
    0.73
     Insert
    0.72
    subs
    0.72
    substitute
    0.71
    Act Density 1.568%

    No Known Activations