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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or doubt

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or appearances of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.77
    pez
    -0.74
     srfAttach
    -0.70
    itton
    -0.69
    odder
    -0.68
    aspers
    -0.67
    izont
    -0.65
     Nanto
    -0.65
    æ©
    -0.63
    pour
    -0.63
    POSITIVE LOGITS
     anymore
    1.18
     bothered
    1.14
     bother
    0.96
     anywhere
    0.89
     necessarily
    0.86
     nor
    0.85
     whatsoever
    0.83
     anything
    0.82
     slightest
    0.79
     remotely
    0.79
    Act Density 0.081%

    No Known Activations