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

    Neuronpedia

    INDEX
    Explanations

    references to communication or expressions of acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     è£
    -0.16
    HEET
    -0.15
    chia
    -0.15
    ansi
    -0.14
    chu
    -0.14
    oux
    -0.14
    ughty
    -0.14
    окÑģи
    -0.14
    çĵľ
    -0.14
    agem
    -0.14
    POSITIVE LOGITS
    encing
    0.31
    iser
    0.30
    ended
    0.30
    ens
    0.27
    ences
    0.25
    ittal
    0.25
    utation
    0.24
    uted
    0.24
    unes
    0.24
    otion
    0.24
    Act Density 0.005%

    No Known Activations