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

    Neuronpedia

    INDEX
    Explanations

    programming code structures

    oai_token-act-pair · gpt-3.5-turbo

    various types of reference markers or links typically used in documentation or web content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.70
    ops
    -0.68
    ĻĤ
    -0.67
    ppy
    -0.67
    mber
    -0.64
     Smy
    -0.62
    ¿½
    -0.62
    acies
    -0.60
     heals
    -0.60
    forms
    -0.60
    POSITIVE LOGITS
    ...]
    0.81
    ].
    0.81
    ],
    0.79
    ashtra
    0.77
    aders
    0.76
     Flavoring
    0.74
     EntityItem
    0.74
     Defendants
    0.73
    =]
    0.72
    20439
    0.71
    Act Density 0.020%

    No Known Activations