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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming and code blocks

    oai_token-act-pair · gpt-3.5-turbo

    repeated non-alphanumeric characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manhattan
    -0.73
    ierrez
    -0.72
     Sic
    -0.69
     dispers
    -0.68
     Mous
    -0.67
    anwhile
    -0.66
     scattering
    -0.66
     segreg
    -0.65
     Franch
    -0.63
     Mutant
    -0.62
    POSITIVE LOGITS
    ľ
    1.49
    ¦
    1.25
    Ń
    1.22
    ¬
    1.20
    ¡
    1.20
    ĺ
    1.14
    º
    1.11
    £
    1.11
    ķ
    1.10
    ł
    1.10
    Act Density 0.256%

    No Known Activations