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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional situations

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the phrase "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holding
    -0.64
    Priv
    -0.62
    package
    -0.60
     estimating
    -0.59
    quartered
    -0.58
     caution
    -0.58
    phia
    -0.58
    ight
    -0.57
     Trouble
    -0.57
     legends
    -0.56
    POSITIVE LOGITS
    chy
    1.11
     happens
    1.00
    alian
    0.98
     rains
    0.98
     ain
    0.97
     mattered
    0.94
     hurts
    0.94
     happened
    0.92
    unes
    0.91
     wasn
    0.89
    Act Density 0.102%

    No Known Activations