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

    Neuronpedia

    INDEX
    Explanations

    questions and the auxiliary verb 'to be' in question form ('is' and 'are')

    oai_token-act-pair · gpt-4-turbo

    questions and statements related to defining or describing something

    oai_token-act-pair · gpt-3.5-turbo

    questions that seek clarification or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gart
    -0.72
    hus
    -0.64
    mates
    -0.60
    tails
    -0.59
    hea
    -0.59
    gra
    -0.57
    jury
    -0.56
    ãĥĥ
    -0.55
    sha
    -0.54
     invitations
    -0.54
    POSITIVE LOGITS
    really
    0.87
     transpired
    0.76
    ?]
    0.74
     REALLY
    0.73
    urger
    0.70
    ?",
    0.69
    ?,
    0.68
    ?:
    0.67
     happened
    0.66
     wrought
    0.65
    Act Density 0.883%

    No Known Activations