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

    Neuronpedia

    INDEX
    Explanations

    sports-related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶ħ
    -0.66
    WP
    -0.61
    "]=>
    -0.60
    WN
    -0.59
    verage
    -0.57
     Coverage
    -0.56
    izon
    -0.56
    lude
    -0.55
    illion
    -0.55
    ĩ
    -0.55
    POSITIVE LOGITS
     respectively
    1.01
     albeit
    1.00
     uh
    0.76
     etc
    0.75
    otos
    0.65
     um
    0.63
     alas
    0.61
     sans
    0.60
    �
    0.58
     according
    0.57
    Act Density 0.552%

    No Known Activations