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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference conditions or parameters related to a specific context or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.15
    agon
    -0.15
    orta
    -0.14
    ÏĩÏĮ
    -0.14
    ses
    -0.14
    etails
    -0.14
    icit
    -0.14
    sez
    -0.13
    ptions
    -0.13
    364
    -0.13
    POSITIVE LOGITS
    Addon
    0.15
    707
    0.15
    rchive
    0.14
    decorators
    0.14
     pur
    0.14
    ény
    0.14
    kee
    0.13
    agate
    0.13
     ngu
    0.13
    uthor
    0.13
    Act Density 0.017%

    No Known Activations