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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fray
    -0.69
     reconstruction
    -0.68
    iasco
    -0.68
     ado
    -0.67
    ongyang
    -0.65
     Topics
    -0.63
     residues
    -0.63
     Strait
    -0.62
     dispute
    -0.62
     developments
    -0.60
    POSITIVE LOGITS
     able
    1.32
     aware
    1.07
     thankful
    0.96
     bitten
    0.94
     ashamed
    0.93
     afraid
    0.93
     complicit
    0.92
     reminded
    0.91
     proud
    0.90
     honest
    0.89
    Act Density 0.866%

    No Known Activations