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

    Neuronpedia

    INDEX
    Explanations

    references to experiences and observations in professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anymore
    -0.19
     nữa
    -0.16
     constant
    -0.15
    appa
    -0.15
    _CB
    -0.15
    bower
    -0.15
     Interval
    -0.14
    Constant
    -0.14
    omers
    -0.14
    ayet
    -0.14
    POSITIVE LOGITS
     countless
    0.35
     plenty
    0.34
     many
    0.30
     numerous
    0.28
     hundreds
    0.26
    many
    0.25
     dozens
    0.24
     Plenty
    0.22
     MANY
    0.22
     thousands
    0.20
    Act Density 0.324%

    No Known Activations