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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or continuity over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Maps
    -0.91
    ouses
    -0.88
    龍喚士
    -0.87
    Released
    -0.86
    ��
    -0.85
    PsyNetMessage
    -0.81
    orage
    -0.80
    othal
    -0.79
    覚醒
    -0.78
    andals
    -0.78
    POSITIVE LOGITS
     term
    0.81
     situation
    0.78
     category
    0.77
     norm
    0.74
     reminder
    0.73
     sentence
    0.72
     environment
    0.69
     counterpart
    0.68
     mor
    0.68
     default
    0.68
    Act Density 0.023%

    No Known Activations