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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating potential actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odable
    -0.17
    shouldBe
    -0.15
    EMPLARY
    -0.15
    erin
    -0.15
    anden
    -0.15
    emu
    -0.15
    lém
    -0.15
    kenin
    -0.15
    anus
    -0.14
    Æ¡
    -0.14
    POSITIVE LOGITS
     nor
    0.29
     mot
    0.24
     bot
    0.22
     net
    0.21
     Nor
    0.21
     note
    0.21
     Note
    0.20
    ot
    0.20
    .note
    0.19
     n
    0.19
    Act Density 0.103%

    No Known Activations