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

    Neuronpedia

    INDEX
    Explanations

    references to stages or performance settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rych
    -0.18
    iglia
    -0.17
    loff
    -0.17
    eps
    -0.16
    rtle
    -0.16
    ne
    -0.16
    apel
    -0.16
    ntag
    -0.15
    ness
    -0.15
    s
    -0.15
    POSITIVE LOGITS
    coach
    0.37
    craft
    0.28
    773
    0.20
    gers
    0.19
    Presence
    0.18
    gy
    0.18
    .Stage
    0.17
    ValuePair
    0.16
     fright
    0.16
    Craft
    0.16
    Act Density 0.025%

    No Known Activations