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

    Neuronpedia

    INDEX
    Explanations

    technical instructions and outlines, such as steps or bullet points

    oai_token-act-pair · gpt-3.5-turbo

    structured data presentation and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gul
    -0.78
     pitching
    -0.75
     pard
    -0.74
     occasion
    -0.72
     cris
    -0.72
     overseas
    -0.72
     bailout
    -0.72
     wiser
    -0.71
     sculpt
    -0.71
     tackling
    -0.70
    POSITIVE LOGITS
    âĢ¢
    1.75
    âĸł
    1.58
    âĹı
    1.55
    ·
    1.40
    âĻ¦
    1.39
    âľ
    1.33
    References
    1.24
    âĸº
    1.24
    First
    1.23
    Official
    1.22
    Act Density 0.165%

    No Known Activations