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
    have
    -1.03
    HAVE
    -0.99
    Have
    -0.95
    were
    -0.91
     Have
    -0.88
    having
    -0.83
    was
    -0.81
    Was
    -0.80
    WAS
    -0.75
     WERE
    -0.75
    POSITIVE LOGITS
     be
    0.74
    liction
    0.46
    ignty
    0.45
    urface
    0.45
    idavit
    0.44
     Sykes
    0.43
    indirizzo
    0.43
    izoen
    0.43
    eliner
    0.42
    cog
    0.42
    Act Density 0.433%

    No Known Activations