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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.56
    thed
    -0.54
    AndGet
    -0.52
    dol
    -0.52
     Region
    -0.51
    章
    -0.50
    OLPH
    -0.50
    WebControls
    -0.49
     endregion
    -0.49
    xus
    -0.49
    POSITIVE LOGITS
     will
    0.68
     may
    0.68
     should
    0.68
     did
    0.66
     has
    0.64
     can
    0.61
     fhould
    0.58
     ſhould
    0.54
     would
    0.53
     must
    0.52
    Act Density 0.534%

    No Known Activations