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

    Neuronpedia

    INDEX
    Explanations

    information related to statistics and facts

    oai_token-act-pair · gpt-3.5-turbo

    references to statistics or factual information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    epad
    -0.58
     Chair
    -0.57
     Iss
    -0.56
     Dictionary
    -0.54
    Incre
    -0.54
    iframe
    -0.53
    idad
    -0.52
     endless
    -0.52
     enough
    -0.51
     Desk
    -0.51
    POSITIVE LOGITS
     perished
    1.06
     originate
    1.00
     belong
    0.99
     reside
    0.93
     belonged
    0.89
     disappeared
    0.88
     vanish
    0.87
     vanished
    0.85
     disappear
    0.81
    went
    0.79
    Act Density 0.715%

    No Known Activations