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

    Neuronpedia

    INDEX
    Explanations

    concepts related to uniqueness and clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ers
    -0.18
    istrovstvÃŃ
    -0.17
    abus
    -0.17
    ysz
    -0.17
    'gc
    -0.16
    able
    -0.16
    erman
    -0.16
     EÅŁ
    -0.15
    (er
    -0.15
    imizer
    -0.15
    POSITIVE LOGITS
    s
    0.23
     factor
    0.22
    sar
    0.18
     levels
    0.18
    0.18
     quotient
    0.17
    -minded
    0.17
    es
    0.17
     level
    0.17
     standards
    0.17
    Act Density 0.324%

    No Known Activations