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

    Neuronpedia

    INDEX
    Explanations

    social media engagement metrics and user interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    c
    -0.64
    m
    -0.60
    d
    -0.59
    i
    -0.59
    p
    -0.58
    b
    -0.56
    t
    -0.56
    y
    -0.56
    a
    -0.56
    n
    -0.55
    POSITIVE LOGITS
    imately
    0.17
    iterated
    0.17
    presso
    0.16
    ncia
    0.15
    shadow
    0.15
    rees
    0.15
    ixels
    0.14
    trap
    0.14
    ilion
    0.14
    forman
    0.14
    Act Density 1.290%

    No Known Activations