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

    Neuronpedia

    INDEX
    Explanations

    references to rankings or positions in lists or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bach
    -0.18
    anz
    -0.17
    uards
    -0.16
     æĸĩç«ł
    -0.15
    ipop
    -0.15
    yte
    -0.14
    _WRAP
    -0.14
     starving
    -0.14
    anges
    -0.14
    ields
    -0.14
    POSITIVE LOGITS
     ten
    0.25
    10
    0.24
    100
    0.20
     ech
    0.20
    20
    0.20
     Ten
    0.19
    _ten
    0.18
     spot
    0.18
    Coder
    0.17
    30
    0.17
    Act Density 0.014%

    No Known Activations