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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with symbols such as 'âĢĶ' and 'âĢĵ'

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paso
    -0.68
     Elys
    -0.64
    Mob
    -0.63
    ciples
    -0.63
     Slug
    -0.61
     Dragons
    -0.60
    oes
    -0.59
     Shant
    -0.58
    orts
    -0.58
    nard
    -0.58
    POSITIVE LOGITS
    albeit
    1.03
    again
    0.98
    perhaps
    0.96
     gasp
    0.90
    almost
    0.87
    ––
    0.86
    along
    0.85
    conserv
    0.81
    quite
    0.80
    surprisingly
    0.79
    Act Density 0.129%

    No Known Activations