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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinions and endorsements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to opinions and evaluations of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Often
    -0.74
    Attempts
    -0.68
    Tier
    -0.68
    Previously
    -0.66
    Series
    -0.65
    Players
    -0.64
    Footnote
    -0.63
    Set
    -0.63
    Although
    -0.61
    uid
    -0.61
    POSITIVE LOGITS
     theirs
    0.86
     hers
    0.83
     ours
    0.82
     goddamn
    0.76
     yours
    0.74
     anything
    0.72
     mine
    0.71
     fucking
    0.67
     airplane
    0.67
     actual
    0.67
    Act Density 0.486%

    No Known Activations