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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being called or summoned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "called" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    feat
    -0.69
    icipated
    -0.62
    edia
    -0.60
    olitics
    -0.60
    ECK
    -0.59
    cest
    -0.58
    BE
    -0.57
    olar
    -0.57
    oday
    -0.56
    tein
    -0.56
    POSITIVE LOGITS
     upon
    1.23
     forth
    1.03
     into
    0.97
     onto
    0.80
     awa
    0.79
     Attention
    0.75
    oused
    0.73
    upon
    0.73
     aloud
    0.72
     attention
    0.72
    Act Density 0.045%

    No Known Activations