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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "something" and its variations emphasizing doing or experiencing various things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anything
    -0.15
    .li
    -0.14
    beck
    -0.14
    خاÙĨÙĩ
    -0.14
    .ColumnHeader
    -0.14
    alom
    -0.14
    aldo
    -0.13
     František
    -0.13
     Kurd
    -0.13
    Secondary
    -0.13
    POSITIVE LOGITS
     else
    0.33
    else
    0.27
    _else
    0.22
    Else
    0.21
     ELSE
    0.21
    	else
    0.20
     Else
    0.20
    ELSE
    0.19
    341
    0.15
     íĦ°
    0.14
    Act Density 0.106%

    No Known Activations