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

    Neuronpedia

    INDEX
    Explanations

    phrases that express indifference or casual acceptance

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

    the word "whatever" within various contexts.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
    Datuak
    -0.66
    :^{
    -0.61
    </tr>
    -0.60
    cls
    -0.60
     Pri
    -0.57
    pri
    -0.55
    Pri
    -0.55
    kras
    -0.54
    みると
    -0.53
     ASTR
    -0.53
    POSITIVE LOGITS
     Whatever
    1.24
    atever
    1.22
    Whatever
    1.17
     whatever
    1.16
     Whoever
    1.10
    whatever
    1.09
    Whoever
    1.09
     whoever
    1.05
     Theſe
    1.01
     itſelf
    1.00
    Act Density 0.063%

    No Known Activations