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

    Neuronpedia

    INDEX
    Explanations

    numerical values and identifiers likely related to items or data points, such as IDs or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.15
    484
    -0.15
    oven
    -0.15
    ologies
    -0.15
    opoulos
    -0.15
    emble
    -0.15
    osaic
    -0.14
    .Point
    -0.14
     Cod
    -0.14
    omi
    -0.14
    POSITIVE LOGITS
    @qq
    0.17
    ãĥ¼ãĥį
    0.16
    .semantic
    0.15
    CursorPosition
    0.15
    logen
    0.15
    _staff
    0.15
    寧
    0.15
    icut
    0.15
    zc
    0.14
     Brook
    0.14
    Act Density 0.040%

    No Known Activations