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

    Neuronpedia

    INDEX
    Explanations

    titles or references related to legends or folklore

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    abus
    -0.69
     Parenthood
    -0.69
    tan
    -0.64
    earcher
    -0.63
    chens
    -0.62
    ters
    -0.60
    chy
    -0.59
     Consent
    -0.59
    ktop
    -0.59
     overflow
    -0.58
    POSITIVE LOGITS
    arily
    1.40
    naire
    0.98
    arium
    0.95
    aries
    0.94
    ous
    0.90
    ocl
    0.89
    ary
    0.79
    arious
    0.78
    lore
    0.77
     tales
    0.75
    Act Density 0.025%

    No Known Activations