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

    Neuronpedia

    INDEX
    Explanations

    words associated with stirring or provoking significant action or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SerializedName
    -0.16
    erland
    -0.16
    arness
    -0.15
    одаÑĢ
    -0.15
    ¯¼
    -0.15
    rani
    -0.15
    loadModel
    -0.14
    uteur
    -0.14
    addin
    -0.14
    lectric
    -0.14
    POSITIVE LOGITS
     Trilogy
    0.15
    jo
    0.14
     Hoy
    0.14
    ja
    0.14
     Stanton
    0.14
     gan
    0.13
     Woo
    0.13
    ¤íĶĦ
    0.13
    ade
    0.13
     Ellis
    0.13
    Act Density 0.000%

    No Known Activations