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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to measurements or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    st
    -0.18
    ../../../
    -0.16
     Ih
    -0.15
    -corner
    -0.15
    stal
    -0.15
    κÏĦη
    -0.14
     Comprehensive
    -0.14
     Candle
    -0.14
    iper
    -0.14
     sched
    -0.14
    POSITIVE LOGITS
    émon
    0.17
    idon
    0.15
    ÑĢок
    0.15
    ERG
    0.15
    ROUP
    0.14
    adoo
    0.14
     Bundy
    0.14
    hetto
    0.14
    ignal
    0.13
    rov
    0.13
    Act Density 0.085%

    No Known Activations