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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a negative consequence or action

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Powered
    -0.72
    doi
    -0.67
    atars
    -0.63
     Tid
    -0.63
    çīĪ
    -0.60
     Osw
    -0.59
    lift
    -0.58
    eatures
    -0.56
     Magnus
    -0.55
    owered
    -0.55
    POSITIVE LOGITS
     nor
    1.51
     therefore
    1.36
     hence
    1.33
     consequently
    1.30
     furthermore
    1.21
     thus
    1.18
     secondly
    1.09
     moreover
    1.06
    yet
    1.03
    Therefore
    0.94
    Act Density 0.284%

    No Known Activations