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

    Neuronpedia

    INDEX
    Explanations

    names of places or entities with unusual characters between them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the symbol "âĢ¦" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icum
    -0.78
     purse
    -0.75
     womb
    -0.74
    grass
    -0.72
    onds
    -0.71
     reper
    -0.71
    oded
    -0.71
     bod
    -0.71
    wagen
    -0.70
    ppings
    -0.66
    POSITIVE LOGITS
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    1.09
    âĢ¦âĢ¦âĢ¦âĢ¦
    1.06
    BUT
    0.91
    etc
    0.83
    ..
    0.81
     Continue
    0.77
     Continued
    0.77
     Written
    0.76
     ,"
    0.76
    Marginal
    0.75
    Act Density 0.012%

    No Known Activations