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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antine
    -0.15
     @"\
    -0.15
    cko
    -0.15
    ascript
    -0.15
    zej
    -0.14
    μμε
    -0.14
    çĿ
    -0.14
    entionPolicy
    -0.14
    azzi
    -0.13
    ideographic
    -0.13
    POSITIVE LOGITS
     else
    0.71
     otherwise
    0.61
    else
    0.57
     Otherwise
    0.54
    	else
    0.53
    Otherwise
    0.48
    otherwise
    0.48
     Else
    0.46
     ELSE
    0.45
    Else
    0.43
    Act Density 0.092%

    No Known Activations