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

    Neuronpedia

    INDEX
    Explanations

    phrases with double hyphens indicating an interruption or change in thought

    oai_token-act-pair · gpt-3.5-turbo

    instances of dashes or hyphens used in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.72
     Madden
    -0.69
     Galile
    -0.68
     cavity
    -0.68
     fue
    -0.67
     dismant
    -0.67
     Hass
    -0.64
     Mechdragon
    -0.63
     substitutes
    -0.63
    iliary
    -0.62
    POSITIVE LOGITS
    notes
    0.96
    fuck
    0.93
    ITS
    0.92
    sil
    0.91
    lance
    0.88
    something
    0.88
    meaning
    0.88
    assisted
    0.87
    multi
    0.86
    requ
    0.85
    Act Density 0.025%

    No Known Activations