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

    Neuronpedia

    INDEX
    Explanations

    conjunctions or phrases that indicate relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ix
    -0.17
    enga
    -0.16
    imb
    -0.16
    rica
    -0.16
    ys
    -0.16
    ager
    -0.15
    ange
    -0.15
    ardon
    -0.15
    elan
    -0.14
    ove
    -0.14
    POSITIVE LOGITS
    :\/\/
    0.15
    this
    0.15
    arlo
    0.15
    EMU
    0.15
    /Peak
    0.14
    Streamer
    0.14
    Č↵
    0.14
     à¤ĩसम
    0.14
     this
    0.14
    skyt
    0.14
    Act Density 0.388%

    No Known Activations