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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating obligation or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĦãĤĭ
    -0.25
    ãģĦãģŁ
    -0.19
    /or
    -0.17
    .au
    -0.16
    ated
    -0.16
    ————————
    -0.15
    ery
    -0.15
    ÂĿ
    -0.15
     behalf
    -0.14
    aphore
    -0.14
    POSITIVE LOGITS
    ร
    0.32
    ìĦľëĬĶ
    0.32
    forth
    0.22
    न
    0.21
    ìĦľ
    0.21
    maal
    0.18
    ย
    0.18
    ment
    0.17
    ëį°
    0.17
    ments
    0.16
    Act Density 0.698%

    No Known Activations