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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving variables

    oai_token-act-pair · gpt-3.5-turbo

    components of programming code, particularly mathematical and logical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chnology
    -0.77
     Niet
    -0.69
    tainment
    -0.68
    indust
    -0.67
    Oracle
    -0.62
     Emblem
    -0.60
     Craigslist
    -0.59
    zona
    -0.59
     encyclopedia
    -0.59
     Anthem
    -0.59
    POSITIVE LOGITS
    ^{
    1.15
    ^
    1.01
    _{
    0.98
    +
    0.95
    âĢ²
    0.94
     =>
    0.92
     :=
    0.92
    âĪĴ
    0.91
     âī¡
    0.90
     <=
    0.90
    Act Density 0.059%

    No Known Activations