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

    Neuronpedia

    INDEX
    Explanations

    times related to specific hours and physical measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical time references and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lank
    -0.60
     dossier
    -0.58
    ctors
    -0.57
    uras
    -0.57
    oÄŁ
    -0.57
    iatrics
    -0.55
    imaru
    -0.55
    raints
    -0.55
    erella
    -0.54
     hood
    -0.54
    POSITIVE LOGITS
     apiece
    1.04
     behest
    0.88
    point
    0.83
    mph
    0.83
    38
    0.80
    34
    0.78
     ripe
    0.76
    54
    0.75
    Hz
    0.74
    omic
    0.74
    Act Density 0.113%

    No Known Activations