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

    Neuronpedia

    INDEX
    Explanations

    a specific character (Ļ) in the text

    oai_token-act-pair · gpt-3.5-turbo

    the repeated character or symbol indicative of frustration or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gmail
    -0.67
     decap
    -0.65
     Codec
    -0.63
     camer
    -0.61
     SMS
    -0.60
     Roma
    -0.59
     tablets
    -0.58
     salads
    -0.58
     GPS
    -0.58
     litter
    -0.58
    POSITIVE LOGITS
    vest
    0.99
    sure
    0.96
    tre
    0.96
    shall
    0.94
    mad
    0.88
    ï¸ı
    0.88
    cre
    0.88
    ve
    0.87
    der
    0.87
    felt
    0.86
    Act Density 0.248%

    No Known Activations