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

    Neuronpedia

    INDEX
    Explanations

    phrases related to frequency distribution or range

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ls
    -0.17
    áºŃt
    -0.17
     gì
    -0.16
    agna
    -0.16
    ulin
    -0.15
    ably
    -0.15
    kest
    -0.14
    ands
    -0.14
    transforms
    -0.14
    iterals
    -0.14
    POSITIVE LOGITS
    -the
    0.21
     spectrum
    0.19
    enger
    0.18
    s
    0.16
     multiple
    0.16
    .documentation
    0.16
    ively
    0.15
    θμ
    0.15
    è¶Ĭ
    0.15
     generations
    0.15
    Act Density 0.029%

    No Known Activations