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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or multiple options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zig
    -0.16
    obao
    -0.15
    RIX
    -0.15
    omi
    -0.15
    öl
    -0.15
     voksne
    -0.14
    owe
    -0.14
    cept
    -0.13
    iola
    -0.13
    åĻ
    -0.13
    POSITIVE LOGITS
    Whatever
    0.32
     whichever
    0.30
     whatever
    0.30
    whatever
    0.30
    Regardless
    0.30
    Anyway
    0.29
     Whatever
    0.28
     Regardless
    0.28
     Anyway
    0.28
     anyway
    0.24
    Act Density 0.175%

    No Known Activations