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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases and concepts emphasizing the significance of certain subjects or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ong
    -0.16
    izard
    -0.14
    jay
    -0.14
    ogg
    -0.14
    iba
    -0.13
    estre
    -0.13
    pair
    -0.13
    lift
    -0.13
    nowled
    -0.13
    rogram
    -0.13
    POSITIVE LOGITS
    heck
    0.15
    Ñĩи
    0.15
    hoe
    0.14
     BEST
    0.14
    enge
    0.14
    że
    0.14
     Interr
    0.14
     best
    0.14
     trick
    0.13
    aleur
    0.13
    Act Density 0.236%

    No Known Activations