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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing meanings or intentions through words

    oai_token-act-pair · gpt-3.5-turbo

    statements conveying strong opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    runner
    -0.71
    ictive
    -0.69
    ogether
    -0.66
    edom
    -0.65
    uries
    -0.65
    estial
    -0.65
    tions
    -0.64
    urable
    -0.64
    ukong
    -0.63
     awaits
    -0.63
    POSITIVE LOGITS
     implicitly
    0.99
     referring
    0.97
     implying
    0.94
     necessarily
    0.83
     tacit
    0.78
     infer
    0.77
     hypoc
    0.77
     kidding
    0.76
     unwittingly
    0.75
     hypocr
    0.75
    Act Density 0.458%

    No Known Activations