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

    Neuronpedia

    INDEX
    Explanations

    contractions and forms of the verb 'to be'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esinden
    -0.15
     scarcely
    -0.15
    awan
    -0.15
    arently
    -0.15
    ibold
    -0.15
     Sure
    -0.15
     pronto
    -0.14
    perhaps
    -0.14
    tright
    -0.14
     EVER
    -0.13
    POSITIVE LOGITS
     such
    0.20
     incumbent
    0.15
     neat
    0.15
     my
    0.15
     important
    0.14
     unreal
    0.14
     funny
    0.14
     carte
    0.13
     frustrating
    0.13
     part
    0.13
    Act Density 0.129%

    No Known Activations