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

    Neuronpedia

    INDEX
    Explanations

    references to new or recent developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andal
    -0.17
     Excell
    -0.15
    fold
    -0.14
     Van
    -0.14
    orpion
    -0.14
    705
    -0.13
     Fort
    -0.13
    Handled
    -0.13
    ranges
    -0.13
    761
    -0.13
    POSITIVE LOGITS
    sworth
    0.22
    bish
    0.19
    -begin
    0.18
    sv
    0.18
    ippi
    0.17
    resas
    0.17
    (Spring
    0.17
    arkers
    0.16
    swire
    0.16
     recruits
    0.16
    Act Density 0.137%

    No Known Activations