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

    Neuronpedia

    INDEX
    Explanations

    data related to percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odore
    -0.15
    à¹īว
    -0.15
    pear
    -0.15
    proof
    -0.15
     Pear
    -0.14
    uns
    -0.14
    xor
    -0.14
    ระ
    -0.14
    ISTIC
    -0.14
    /libs
    -0.14
    POSITIVE LOGITS
    rale
    0.17
    aires
    0.17
    iles
    0.16
    oriously
    0.16
    -plus
    0.16
    atively
    0.15
    ivals
    0.15
    ally
    0.15
     gross
    0.15
    ì§ľ
    0.15
    Act Density 0.018%

    No Known Activations