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

    Neuronpedia

    INDEX
    Explanations

    terms indicating the level or degree of something, particularly in relation to uncertainty or explicitness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.79
    iris
    -0.77
    etheless
    -0.77
    RTCF
    -0.76
     philosophic
    -0.75
    ıç
    -0.74
     Siro
    -0.73
    <?
    -0.72
     Helios
    -0.72
     mangoes
    -0.70
    POSITIVE LOGITS
     Ext
    1.07
     ext
    1.03
    ext
    0.99
    Ext
    0.97
    Extent
    0.87
     advocate
    0.79
     EXT
    0.77
    xtype
    0.75
    +#+#
    0.72
    EXT
    0.71
    Act Density 0.097%

    No Known Activations