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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or reason

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.64
    makeText
    -0.54
    下载附件
    -0.53
    maschinen
    -0.52
    мна
    -0.51
    isks
    -0.51
    lliant
    -0.50
    JNIEnv
    -0.49
    össä
    -0.49
    izzling
    -0.49
    POSITIVE LOGITS
    ScopeManager
    0.83
     reasons
    0.81
    ագրություններ
    0.72
    reasons
    0.64
     kasarigan
    0.63
    RenderAtEndOf
    0.62
     instance
    0.61
     transférez
    0.61
     example
    0.59
    abestanden
    0.58
    Act Density 0.372%

    No Known Activations