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

    Neuronpedia

    INDEX
    Explanations

    references or citations in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çIJ³
    -0.16
    foy
    -0.16
    ĺ
    -0.16
    sWith
    -0.16
    //{{
    -0.16
    edException
    -0.15
    sson
    -0.15
    inn
    -0.15
    rum
    -0.14
    edImage
    -0.14
    POSITIVE LOGITS
    ://
    0.17
    elman
    0.16
    KN
    0.15
    inality
    0.14
     Arms
    0.14
    quential
    0.14
    orrent
    0.14
    adel
    0.14
    mare
    0.13
    ophon
    0.13
    Act Density 0.010%

    No Known Activations