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

    Neuronpedia

    INDEX
    Explanations

    structures and relationships involving triples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zsche
    -0.55
     szóci
    -0.52
    ItemBackground
    -0.51
    ariate
    -0.51
     Tenth
    -0.49
    الدراسه
    -0.49
     arrend
    -0.48
     itſelf
    -0.47
    󠁢
    -0.47
    gebouw
    -0.47
    POSITIVE LOGITS
     trio
    1.11
     three
    1.02
    three
    0.99
     triad
    0.98
    三
    0.98
    THREE
    0.91
    Three
    0.90
     Trio
    0.89
     Three
    0.87
     مشين
    0.87
    Act Density 1.175%

    No Known Activations