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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Injector
    -0.20
    raf
    -0.16
    .union
    -0.16
    ustum
    -0.15
    ransition
    -0.15
    åĭĻ
    -0.14
    adil
    -0.14
    ombok
    -0.14
    ób
    -0.14
    beck
    -0.14
    POSITIVE LOGITS
     actual
    0.16
    Actual
    0.15
    ailer
    0.15
    ELSE
    0.15
     Actual
    0.15
    onde
    0.15
    RESSED
    0.15
    otherwise
    0.15
    zzo
    0.14
    actual
    0.14
    Act Density 0.121%

    No Known Activations