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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and operations related to functions or components in programming or engineering contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elson
    -0.16
    ìĥģ
    -0.16
     Sour
    -0.15
    estre
    -0.15
     Brewing
    -0.15
    ampo
    -0.15
    chaft
    -0.14
    appa
    -0.14
     ><?
    -0.14
    udget
    -0.14
    POSITIVE LOGITS
     God
    0.24
    god
    0.21
     god
    0.20
    God
    0.20
     Variant
    0.20
    variant
    0.19
    Variant
    0.19
    .variant
    0.18
     variant
    0.18
    	ERR
    0.17
    Act Density 0.000%

    No Known Activations