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

    Neuronpedia

    INDEX
    Explanations

    programming syntax with arrows and comparison operators

    oai_token-act-pair · gpt-3.5-turbo

    coding syntax and expressions involving functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.86
    iple
    -0.85
    alach
    -0.79
    lasses
    -0.71
    ernel
    -0.69
    vae
    -0.68
    etsk
    -0.68
    uum
    -0.68
    rament
    -0.68
    hum
    -0.68
    POSITIVE LOGITS
     {"
    0.77
     Mongo
    0.72
     println
    0.71
     Ùħ
    0.71
    ï¸
    0.68
     ({
    0.68
    ions
    0.66
    ÙĨ
    0.65
    س
    0.63
     Became
    0.62
    Act Density 0.018%

    No Known Activations