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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a negative perception or judgment of a situation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "all too" in various contexts of overuse or excess

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agara
    -0.78
    ahime
    -0.77
    ersion
    -0.71
    utenberg
    -0.71
    cius
    -0.70
    agra
    -0.68
    cheat
    -0.65
    ushi
    -0.63
    EStream
    -0.62
    agna
    -0.62
    POSITIVE LOGITS
    ÏĤ
    0.64
    Reloaded
    0.62
    ~~~~~~~~
    0.62
    SAM
    0.59
    lihood
    0.58
    nuts
    0.57
     omin
    0.55
    Todd
    0.54
    Round
    0.54
    ira
    0.53
    Act Density 0.045%

    No Known Activations