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

    Neuronpedia

    INDEX
    Explanations

    the concept of persistence or continuity in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſche
    -0.92
     ſch
    -0.91
     ſy
    -0.90
     pleaſure
    -0.90
     ſou
    -0.82
     ſever
    -0.81
     Inſ
    -0.81
     ſol
    -0.81
     ſon
    -0.80
     ſte
    -0.79
    POSITIVE LOGITS
     remains
    1.13
     remain
    1.13
     remained
    1.00
    remain
    0.96
     Remain
    0.95
    remains
    0.93
    Remain
    0.90
     Remains
    0.89
     rimane
    0.80
     demeure
    0.76
    Act Density 0.115%

    No Known Activations