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

    Neuronpedia

    INDEX
    Explanations

    the word "whatever" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    en
    -0.75
     \
    -0.68
    I
    -0.66
    i
    -0.64
     I
    -0.64
    .
    -0.63
    liferay
    -0.62
    н
    -0.62
     in
    -0.61
     as
    -0.59
    POSITIVE LOGITS
     Whatever
    1.51
    Whatever
    1.44
    whatever
    1.41
     whatever
    1.39
    atever
    1.36
     whichever
    1.31
     Theſe
    1.28
     Whoever
    1.25
     whoever
    1.24
     itſelf
    1.22
    Act Density 0.058%

    No Known Activations