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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a list of items or attributes

    oai_token-act-pair · gpt-3.5-turbo

    lists or categories of related items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾į
    -0.54
    çĶ°
    -0.54
    İ
    -0.53
    Ĭ±
    -0.51
    WHERE
    -0.51
    :\
    -0.50
    theless
    -0.49
    :(
    -0.49
    :[
    -0.48
    ":"/
    -0.48
    POSITIVE LOGITS
     etc
    1.62
    etc
    1.34
     and
    1.30
     &
    1.10
    and
    0.97
     or
    0.95
     et
    0.94
     AND
    0.91
     ect
    0.89
    whatever
    0.74
    Act Density 0.249%

    No Known Activations