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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating scientific concepts and their relationships, particularly in the context of models and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ou
    -0.14
     chrono
    -0.14
    avern
    -0.13
    .untracked
    -0.13
    Ny
    -0.13
     escorte
    -0.13
    æĭ
    -0.13
    oso
    -0.13
    å§ĵ
    -0.13
     czas
    -0.13
    POSITIVE LOGITS
     transition
    0.34
     phase
    0.32
     transitions
    0.30
    transition
    0.29
     Transition
    0.29
    ransition
    0.28
    _transition
    0.27
    Transition
    0.26
    phase
    0.25
    Phase
    0.24
    Act Density 0.009%

    No Known Activations