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

    Neuronpedia

    INDEX
    Explanations

    words related to symbols, representations, and indications

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to representation or indication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kees
    -0.87
    BILL
    -0.76
    utsu
    -0.76
    athy
    -0.74
    ilers
    -0.74
    athi
    -0.74
     Carbuncle
    -0.72
    boot
    -0.70
     Sabha
    -0.69
    pour
    -0.69
    POSITIVE LOGITS
     pronunciation
    0.76
     how
    0.75
     landmarks
    0.74
     qualities
    0.73
     something
    0.72
     eternity
    0.72
     individuality
    0.71
     disrespect
    0.70
     uniqueness
    0.68
     integer
    0.68
    Act Density 0.180%

    No Known Activations