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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions indicating intent or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isty
    -0.15
    ASSERT
    -0.15
    ensing
    -0.14
     prose
    -0.14
    sted
    -0.14
    939
    -0.14
    adic
    -0.13
    ä¸Ī
    -0.13
     se
    -0.13
     soon
    -0.13
    POSITIVE LOGITS
     attending
    0.22
     accept
    0.17
     canyon
    0.17
     columnist
    0.16
    cate
    0.16
     allegation
    0.16
     bana
    0.16
     charge
    0.16
    -face
    0.16
    igu
    0.16
    Act Density 0.003%

    No Known Activations