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

    Neuronpedia

    INDEX
    Explanations

    structural elements within a text, such as introductory phrases and transitions

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "similarly" or phrases that compare similar ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Engineers
    -0.68
    ãĥ¥
    -0.66
    Deal
    -0.65
    interstitial
    -0.59
    Cause
    -0.58
    assed
    -0.57
    Associated
    -0.57
     enthus
    -0.57
    Accessory
    -0.56
    offs
    -0.56
    POSITIVE LOGITS
     however
    1.24
     though
    0.92
     although
    0.86
     meanwhile
    0.85
     please
    0.84
     according
    0.79
     moreover
    0.78
     albeit
    0.71
     alas
    0.70
    dds
    0.69
    Act Density 0.468%

    No Known Activations