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

    Neuronpedia

    INDEX
    Explanations

    roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    words related to literary works or novels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ̶
    -0.72
    gypt
    -0.70
     Methodist
    -0.65
     Lever
    -0.64
    Wi
    -0.63
     Zombie
    -0.61
    visor
    -0.61
     Lund
    -0.60
     Camb
    -0.60
     Hyder
    -0.60
    POSITIVE LOGITS
    urnal
    0.90
    onyms
    0.79
    theless
    0.76
    xious
    0.74
    TPPStreamerBot
    0.72
    agon
    0.68
     whatsoever
    0.67
    Else
    0.67
    ODY
    0.65
    seekers
    0.64
    Act Density 0.044%

    No Known Activations