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

    Neuronpedia

    INDEX
    Explanations

    words related to various physical bodily functions and conditions

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "read" and terms related to judgment or critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tanz
    -0.74
     warr
    -0.69
     initials
    -0.67
     adop
    -0.65
     referen
    -0.64
     perpend
    -0.60
     toget
    -0.60
     laun
    -0.58
     operating
    -0.57
    ãĥ£
    -0.57
    POSITIVE LOGITS
    FUL
    1.35
    ful
    1.31
    fulness
    1.26
    lessly
    1.13
    fully
    1.12
    ously
    1.10
    lessness
    1.01
    iness
    0.92
    less
    0.92
    lust
    0.91
    Act Density 0.169%

    No Known Activations