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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accepting or rejecting opportunities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rejection or turning down offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disbanded
    -0.78
    ĪĴ
    -0.74
     dismantled
    -0.73
    construct
    -0.70
    sembly
    -0.68
     timestamp
    -0.67
     testament
    -0.67
     ledger
    -0.66
    minus
    -0.65
     taped
    -0.64
    POSITIVE LOGITS
     lure
    1.04
     tempt
    1.03
     enticing
    0.95
     attractive
    0.93
     prostitutes
    0.91
     temptation
    0.90
     Seeking
    0.90
     exotic
    0.87
     tempting
    0.86
     prey
    0.85
    Act Density 0.500%

    No Known Activations