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

    Neuronpedia

    INDEX
    Explanations

    references to traditional concepts, styles, or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .EventType
    -0.15
    writer
    -0.15
    enta
    -0.14
    eya
    -0.14
    163
    -0.14
    ãģ¹ãģį
    -0.14
    erra
    -0.14
    493
    -0.13
    Descriptors
    -0.13
    emic
    -0.13
    POSITIVE LOGITS
    hma
    0.17
    itionally
    0.16
    lue
    0.16
    ists
    0.15
    CDF
    0.15
    uros
    0.15
    ziel
    0.15
    éĢļãĤĬ
    0.15
    visor
    0.15
    shal
    0.14
    Act Density 0.025%

    No Known Activations