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

    Neuronpedia

    INDEX
    Explanations

    phrases related to horror or extreme adversity

    oai_token-act-pair · gpt-3.5-turbo

    the repeated pattern of a specific letter sequence, likely 'ij'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yards
    -0.72
    女
    -0.69
    ACTED
    -0.69
     flux
    -0.69
     interchangeable
    -0.66
     Willow
    -0.63
     comparable
    -0.62
     Ranger
    -0.62
     bleach
    -0.62
    ŃĶ
    -0.61
    POSITIVE LOGITS
    ournal
    1.13
    eh
    1.08
    utsu
    1.00
    ohn
    0.96
    ij
    0.94
    unal
    0.94
    unction
    0.94
    ansen
    0.87
    abad
    0.87
    ansson
    0.87
    Act Density 0.008%

    No Known Activations