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

    Neuronpedia

    INDEX
    Explanations

    dramatic language and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalTable
    -0.50
     Familienname
    -0.40
    AnchorTagHelper
    -0.40
    guigu
    -0.35
    UnsafeEnabled
    -0.34
     confronti
    -0.33
    principalColumn
    -0.33
    tiéndose
    -0.32
     twar
    -0.32
     estekak
    -0.32
    POSITIVE LOGITS
     dramatic
    0.86
    Dramatic
    0.84
    dramatic
    0.84
     Dramatic
    0.79
     dram
    0.79
    dram
    0.72
     theat
    0.68
     dramatically
    0.65
     exaggerate
    0.64
     drama
    0.63
    Act Density 0.481%

    No Known Activations