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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating subsequent actions or events in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikä
    -0.67
     Morty
    -0.62
    لينا
    -0.60
    nasium
    -0.59
     المعيارى
    -0.57
     carni
    -0.57
    itecture
    -0.55
     Pyrr
    -0.55
    Carla
    -0.54
     Pey
    -0.54
    POSITIVE LOGITS
     Following
    1.06
    Following
    1.05
     following
    1.02
     FOLLOWING
    0.90
    Portail
    0.89
    following
    0.89
     Morin
    0.86
    ]='\
    0.83
     after
    0.83
     numerous
    0.82
    Act Density 0.026%

    No Known Activations