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

    Neuronpedia

    INDEX
    Explanations

    terms related to communication and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampo
    -0.20
    arness
    -0.16
    $route
    -0.15
    ennent
    -0.15
    vit
    -0.14
    acket
    -0.14
    ibling
    -0.14
    _construct
    -0.14
     Ear
    -0.14
    AILY
    -0.14
    POSITIVE LOGITS
     means
    0.24
    Means
    0.20
    means
    0.20
     Means
    0.20
     sources
    0.18
     Sources
    0.17
     Mode
    0.17
     forms
    0.17
    -mode
    0.17
    eki
    0.17
    Act Density 0.028%

    No Known Activations