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

    Neuronpedia

    INDEX
    Explanations

    terms related to promotion and advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ild
    -0.18
    ern
    -0.16
    von
    -0.15
    hood
    -0.15
    VERRIDE
    -0.14
    any
    -0.14
    NA
    -0.14
    itude
    -0.14
    iron
    -0.14
     onDataChange
    -0.14
    POSITIVE LOGITS
    /prom
    0.22
    Å¡ak
    0.17
    inin
    0.15
    utut
    0.15
    yš
    0.15
    placer
    0.14
    atively
    0.14
    stp
    0.14
    stable
    0.14
     Burl
    0.14
    Act Density 0.031%

    No Known Activations