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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate interaction or interconnectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    řízení
    -0.48
    bezpiec
    -0.47
    bezpiecz
    -0.47
    AnimationsModule
    -0.44
    nimmt
    -0.44
    DMETHOD
    -0.43
    bezpe
    -0.42
    łoż
    -0.41
    tragen
    -0.37
    wards
    -0.36
    POSITIVE LOGITS
    scope
    0.56
    safe
    0.53
    ship
    0.52
    slip
    0.51
    StoryboardSegue
    0.49
    shah
    0.49
    sha
    0.48
    elemField
    0.48
    دانشنامهٔ
    0.48
    soft
    0.47
    Act Density 0.358%

    No Known Activations