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

    Neuronpedia

    INDEX
    Explanations

    negative expressions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unter
    -0.18
    bourg
    -0.16
    ا
    -0.15
    %s
    -0.15
    ’T
    -0.15
    reed
    -0.15
     ÙĢ
    -0.15
     âĢķ
    -0.15
    सम
    -0.15
    ’na
    -0.15
    POSITIVE LOGITS
    /-
    0.26
    /+
    0.24
     "
    0.23
    _-
    0.23
    webkit
    0.21
     -↵
    0.21
     ("
    0.20
    .-
    0.20
     -
    0.19
     '
    0.19
    Act Density 0.120%

    No Known Activations