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

    Neuronpedia

    INDEX
    Explanations

    invitations or requirements for certain actions in a given context

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with invitations, requirements, and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Allen
    -0.62
    tra
    -0.60
     bush
    -0.58
     Sack
    -0.58
     Ain
    -0.57
     stain
    -0.57
    Us
    -0.57
     vein
    -0.56
    rival
    -0.55
     reson
    -0.55
    POSITIVE LOGITS
    ĸļ
    0.90
    ©¶æ¥µ
    0.82
     aback
    0.79
    ptin
    0.76
     somew
    0.71
    untarily
    0.70
    Ń·
    0.70
    £ı
    0.69
    anwhile
    0.68
    lear
    0.68
    Act Density 0.176%

    No Known Activations