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

    Neuronpedia

    INDEX
    Explanations

    instances of strong emotional or critical statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagHelpers
    -0.57
    -
    -0.54
    2
    -0.54
    8
    -0.54
     Turned
    -0.54
    4
    -0.54
     
    -0.54
     weird
    -0.52
    3
    -0.52
    o
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    1.00
     ainfi
    1.00
    EndGlobalSection
    0.99
     quæ
    0.98
     auffi
    0.97
     ejus
    0.96
     habet
    0.93
     pleaſure
    0.92
    UnsafeEnabled
    0.92
    /**
    0.92
    Act Density 0.430%

    No Known Activations