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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "whatever" used for dismissive or vague purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Whatever" followed by a comma or other words

    np_acts-logits-general · gemini-2.0-flash

    Whatever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -1.10
    Diwedd
    -0.72
     Audiodateien
    -0.70
    findpost
    -0.68
     للمعارف
    -0.63
    LayoutStyle
    -0.63
     anise
    -0.60
    :^{
    -0.59
    TagMode
    -0.59
    dymyr
    -0.58
    POSITIVE LOGITS
     else
    0.98
     Whatever
    0.71
     whatever
    0.67
    Whatever
    0.67
     Warburton
    0.66
     happens
    0.65
    kolwiek
    0.64
    cinogen
    0.64
    Whoever
    0.63
     whoever
    0.63
    Act Density 0.038%

    No Known Activations