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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest comparisons and evaluations of quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oge
    -0.15
    æĬŀ
    -0.14
    ippi
    -0.14
    odzi
    -0.14
     asÃŃ
    -0.13
    DownList
    -0.13
    Certain
    -0.13
     Certain
    -0.13
    ORIZED
    -0.13
    ool
    -0.13
    POSITIVE LOGITS
     ones
    1.39
     Ones
    0.91
    ones
    0.84
    ONES
    0.52
    ãĤĤãģ®
    0.52
    .ones
    0.45
     others
    0.37
     ours
    0.36
     theirs
    0.34
     yours
    0.34
    Act Density 0.231%

    No Known Activations