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

    Neuronpedia

    INDEX
    Explanations

    variations of the root word "des" indicating negation or a reversal of state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warz
    -0.18
    ä¸Ī
    -0.18
    ãĥ¼ãĥľ
    -0.16
    sie
    -0.16
    czy
    -0.15
    μή
    -0.15
     sie
    -0.15
    rections
    -0.14
    梨
    -0.14
    clid
    -0.14
    POSITIVE LOGITS
    anmar
    0.17
    emb
    0.16
    plet
    0.15
    pagesize
    0.15
    æ¸
    0.15
    afi
    0.15
    aires
    0.15
    ees
    0.15
    lices
    0.15
    odor
    0.15
    Act Density 0.005%

    No Known Activations