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

    Neuronpedia

    INDEX
    Explanations

    references to various powers and abilities, particularly in a legal or regulatory context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arend
    -0.17
    bish
    -0.17
    -overlay
    -0.16
    aghan
    -0.15
    ingleton
    -0.15
     rocket
    -0.14
    atory
    -0.14
    asje
    -0.14
    unnel
    -0.14
    iffe
    -0.14
    POSITIVE LOGITS
    ActionCreators
    0.18
    fully
    0.17
    735
    0.15
    .va
    0.14
    تØŃ
    0.14
    .gravity
    0.14
    .scalablytyped
    0.14
    ô
    0.14
    com
    0.14
    uw
    0.14
    Act Density 0.020%

    No Known Activations