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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between concepts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    croll
    -0.64
     rarest
    -0.55
    réhen
    -0.54
    Slik
    -0.53
     Waray
    -0.53
    prehensive
    -0.53
    omenclature
    -0.53
    ianum
    -0.53
     ske
    -0.52
    chige
    -0.51
    POSITIVE LOGITS
     that
    1.13
     bahwa
    1.03
     وأن
    0.97
     rằng
    0.91
     bahawa
    0.77
     ότι
    0.71
     kwamba
    0.70
     πως
    0.68
     dass
    0.66
     noting
    0.65
    Act Density 0.459%

    No Known Activations