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

    Neuronpedia

    INDEX
    Explanations

    terms related to interpretation and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fant
    -0.15
    aj
    -0.15
    vise
    -0.15
    iç
    -0.14
     Guth
    -0.14
    lund
    -0.14
    ylvania
    -0.14
    iew
    -0.14
    /mat
    -0.13
    sg
    -0.13
    POSITIVE LOGITS
    ationship
    0.16
    mez
    0.16
    hin
    0.15
    .dictionary
    0.15
    RIORITY
    0.15
    atively
    0.15
     Analyst
    0.14
     gezocht
    0.14
    undos
    0.14
    riba
    0.14
    Act Density 0.029%

    No Known Activations