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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coal
    -0.16
    enment
    -0.15
     compile
    -0.15
    createClass
    -0.14
    bservable
    -0.13
     Roths
    -0.13
    reira
    -0.13
    arters
    -0.13
    ependency
    -0.13
    issance
    -0.13
    POSITIVE LOGITS
    ANGO
    0.15
    APPER
    0.14
    ACHE
    0.14
    ATUS
    0.14
    ozy
    0.14
    uni
    0.14
    åij
    0.14
    âu
    0.14
    apper
    0.13
    .tw
    0.13
    Act Density 0.098%

    No Known Activations