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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frustration or disappointment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzi
    -0.72
    gan
    -0.71
    yan
    -0.70
    hole
    -0.68
    bern
    -0.65
    agin
    -0.65
    shaw
    -0.64
    akia
    -0.64
    anza
    -0.63
    hal
    -0.63
    POSITIVE LOGITS
    soever
    1.33
     confronted
    0.83
     faced
    0.80
     contrasted
    0.79
     compared
    0.77
    irlf
    0.76
     comparing
    0.75
    fy
    0.73
    theless
    0.72
    anguage
    0.69
    Act Density 0.108%

    No Known Activations