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

    Neuronpedia

    INDEX
    Explanations

    statistics and numerical data related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alse
    -0.16
    panse
    -0.14
    olia
    -0.13
    keh
    -0.13
     uphill
    -0.13
     Forward
    -0.13
    witter
    -0.13
     вÑģего
    -0.13
    _CO
    -0.13
     Less
    -0.13
    POSITIVE LOGITS
     close
    0.32
     closer
    0.31
     somewhere
    0.30
     north
    0.30
     approaching
    0.28
    appro
    0.25
     around
    0.25
    Appro
    0.25
     above
    0.25
     anywhere
    0.25
    Act Density 0.260%

    No Known Activations