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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and phrases indicating necessity, obligation, or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    crest
    -0.20
    HAVE
    -0.17
     зави
    -0.15
    IENT
    -0.15
    аÑĪ
    -0.15
     HAVE
    -0.15
    Have
    -0.15
    ResourceId
    -0.14
     завиÑģим
    -0.14
    HLT
    -0.14
    POSITIVE LOGITS
     bed
    0.24
     kept
    0.22
     brought
    0.22
     beden
    0.20
     ber
    0.19
     examined
    0.19
     ben
    0.19
     me
    0.19
     carried
    0.19
     distributed
    0.19
    Act Density 0.256%

    No Known Activations