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

    Neuronpedia

    INDEX
    Explanations

    specific references and identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocha
    -0.16
    oÅĽci
    -0.15
    cpy
    -0.15
     Cab
    -0.15
    cab
    -0.15
    Cab
    -0.15
    eniable
    -0.14
    ancel
    -0.14
    RIES
    -0.14
    oire
    -0.14
    POSITIVE LOGITS
    ourn
    0.15
     harm
    0.14
    atal
    0.14
     æIJ
    0.14
     Harm
    0.14
    het
    0.14
    даÑĤ
    0.14
     Invest
    0.14
    _AA
    0.13
     opportun
    0.13
    Act Density 0.016%

    No Known Activations