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

    Neuronpedia

    INDEX
    Explanations

    requests or invitations in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing conditional offers or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brill
    -0.69
     Trap
    -0.63
     Kiw
    -0.61
    è¦ļéĨĴ
    -0.58
     Od
    -0.58
    \<
    -0.55
     aster
    -0.55
     Scand
    -0.55
     Prot
    -0.53
     prosecut
    -0.53
    POSITIVE LOGITS
     prefer
    1.30
     dearly
    1.09
     gladly
    1.07
     like
    1.03
     LIKE
    0.91
    igslist
    0.90
    rather
    0.89
     appreciate
    0.87
     kindly
    0.86
    like
    0.86
    Act Density 0.113%

    No Known Activations