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

    Neuronpedia

    INDEX
    Explanations

    references to unique characteristics or exclusive features in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unma
    -0.15
    anoi
    -0.15
    otron
    -0.15
    ÑģÑĤÑĢÑĥк
    -0.13
    usk
    -0.13
     biri
    -0.13
    zb
    -0.13
     LIABLE
    -0.13
    USES
    -0.13
    orus
    -0.13
    POSITIVE LOGITS
     exclusive
    0.80
     unique
    0.71
    exclusive
    0.69
     Exclusive
    0.67
     exclus
    0.67
    Exclusive
    0.66
    -exclusive
    0.65
    unique
    0.62
     Unique
    0.61
     uniqueness
    0.60
    Act Density 0.260%

    No Known Activations