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

    Neuronpedia

    INDEX
    Explanations

    religious/spiritual language or scriptures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and structures that denote separation or lists in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.92
    ggy
    -0.80
    taboola
    -0.77
    phas
    -0.74
    DAQ
    -0.73
    odcast
    -0.72
    ppy
    -0.71
    eki
    -0.70
    Focus
    -0.69
    Tip
    -0.69
    POSITIVE LOGITS
     viz
    1.41
     wherein
    1.20
     whence
    1.20
     whereby
    1.18
     yea
    1.15
     notwithstanding
    1.11
     whilst
    1.08
     doubtless
    1.06
     namely
    1.04
     whereas
    1.02
    Act Density 0.298%

    No Known Activations