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

    Neuronpedia

    INDEX
    Explanations

    words with special characters or formatting like accents, symbols, and initials

    oai_token-act-pair · gpt-3.5-turbo

    character names or titles within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disadvant
    -0.93
     misunder
    -0.84
     Vaugh
    -0.75
    nesday
    -0.71
     levers
    -0.70
     carbohyd
    -0.68
     fundament
    -0.67
     harness
    -0.67
    edIn
    -0.64
     condem
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.02
     âĢº
    0.88
    cffffcc
    0.82
    ļ
    0.76
    ×
    0.72
    ½
    0.72
    °
    0.71
    İ
    0.69
    и
    0.68
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.68
    Act Density 0.167%

    No Known Activations