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

    Neuronpedia

    INDEX
    Explanations

    numbers in the format of '5' followed by another number

    oai_token-act-pair · gpt-3.5-turbo

    markers indicating the end of text or section breaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.64
    icol
    -0.64
     Hort
    -0.64
    worldly
    -0.60
    xual
    -0.60
    mia
    -0.60
    opter
    -0.59
     Hunts
    -0.59
     bapt
    -0.59
    perature
    -0.58
    POSITIVE LOGITS
    Thirty
    1.19
    âĺħ
    0.85
    th
    0.82
    010
    0.82
    678
    0.81
    0000
    0.77
    43
    0.77
    anging
    0.75
    pb
    0.74
     ILCS
    0.74
    Act Density 0.115%

    No Known Activations