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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an excessive or undesirable amount of something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "all too" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    instein
    -0.83
    etsk
    -0.78
    hess
    -0.72
    yout
    -0.72
    cius
    -0.67
    aea
    -0.66
    raise
    -0.66
    DF
    -0.65
    ersion
    -0.64
    oust
    -0.63
    POSITIVE LOGITS
    entimes
    0.81
     prevalent
    0.78
     evident
    0.77
     painfully
    0.77
     familiar
    0.75
     often
    0.74
     eager
    0.74
    often
    0.72
     recogn
    0.69
     predictable
    0.68
    Act Density 0.045%

    No Known Activations