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

    Neuronpedia

    INDEX
    Explanations

    references to academic or scholarly achievements and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardo
    -0.16
    andum
    -0.14
    addComponent
    -0.14
    obierno
    -0.13
    utters
    -0.13
    å®ĥ
    -0.13
    еÑī
    -0.13
    ivative
    -0.12
    _stamp
    -0.12
     itself
    -0.12
    POSITIVE LOGITS
     these
    0.42
     each
    0.40
    è¿ĻäºĽ
    0.39
    åIJĦ
    0.37
    these
    0.37
    each
    0.36
    These
    0.35
     These
    0.34
     ê°ģ
    0.33
     åIJĦ
    0.32
    Act Density 0.817%

    No Known Activations