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

    Neuronpedia

    INDEX
    Explanations

    the word "whatever" and variations of it, indicating a search for expressions of indifference or non-specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     INTERESAR
    -0.57
    isContained
    -0.53
     Dat
    -0.51
    QUIR
    -0.50
    idente
    -0.49
    Dat
    -0.49
    
    -0.49
     Le
    -0.48
    awtextra
    -0.48
    المناصب
    -0.47
    POSITIVE LOGITS
     whatever
    1.04
    whatever
    0.91
     itſelf
    0.91
     Whatever
    0.90
     himſelf
    0.87
     rare
    0.86
    Whatever
    0.86
     purpoſe
    0.85
     whoſe
    0.81
     themſelves
    0.81
    Act Density 0.084%

    No Known Activations