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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _sd
    -0.18
    chia
    -0.15
    apolis
    -0.15
    uars
    -0.14
    ilen
    -0.14
    tha
    -0.14
    CEED
    -0.14
    emark
    -0.14
    jack
    -0.14
     jack
    -0.14
    POSITIVE LOGITS
     soon
    0.18
     shortly
    0.17
     Fam
    0.17
     Dee
    0.17
    soon
    0.17
    recall
    0.16
    amiliar
    0.15
    andi
    0.15
     recall
    0.14
    ibri
    0.14
    Act Density 0.050%

    No Known Activations