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

    Neuronpedia

    INDEX
    Explanations

    high-value numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "?"
    -1.77
    ennis
    -1.71
    uppose
    -1.64
    board
    -1.48
     rarely
    -1.45
    ectomy
    -1.44
    ace
    -1.43
    ]>
    -1.40
    onia
    -1.36
    antes
    -1.34
    POSITIVE LOGITS
    ®
    2.76
    ¾
    2.47
    Ĵ
    2.40
    Ľ
    2.37
    µ
    2.16
    ³
    2.14
    ī
    2.01
    ħ
    2.00
    ª
    2.00
    1.97
    Act Density 0.014%

    No Known Activations