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

    Neuronpedia

    INDEX
    Explanations

    mentions of numerical data and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.88
    DockStyle
    -0.80
    +#+#
    -0.77
    Autoritní
    -0.76
     مشين
    -0.76
    RectangleBorder
    -0.73
     cannibal
    -0.70
    省市镇
    -0.69
     Dormit
    -0.68
     photolibrary
    -0.68
    POSITIVE LOGITS
     but
    0.48
     Tim
    0.46
    _
    0.46
     C
    0.45
    _.
    0.45
     we
    0.44
     host
    0.43
    ist
    0.43
    wo
    0.43
     why
    0.43
    Act Density 0.510%

    No Known Activations