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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that indicate hypothetical or uncertain scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amble
    -0.15
    quo
    -0.15
    itsu
    -0.14
    ilha
    -0.14
    olk
    -0.14
    ahun
    -0.14
    or
    -0.14
    oram
    -0.14
     birlik
    -0.13
    ÐĶÐļ
    -0.13
    POSITIVE LOGITS
    vertime
    0.15
    VERR
    0.14
    thon
    0.14
    utc
    0.14
    weg
    0.14
    leigh
    0.14
    anton
    0.14
    itos
    0.13
    ScreenWidth
    0.13
    ake
    0.13
    Act Density 0.092%

    No Known Activations