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

    Neuronpedia

    INDEX
    Explanations

    words related to peculiarity or unusualness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "odd" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.82
    uberty
    -0.78
    uden
    -0.74
    çīĪ
    -0.70
    apers
    -0.69
    chen
    -0.69
    ilitating
    -0.67
    cussion
    -0.67
    ASED
    -0.67
    igate
    -0.67
    POSITIVE LOGITS
    ities
    1.19
    ball
    1.15
    balls
    1.04
    ity
    0.89
     numbered
    0.86
    yssey
    0.83
    ishly
    0.81
     occurrences
    0.80
    worldly
    0.78
    flake
    0.75
    Act Density 0.016%

    No Known Activations