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

    Neuronpedia

    INDEX
    Explanations

    expressions of intention or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingo
    -0.17
    izo
    -0.17
    eso
    -0.16
    andes
    -0.15
    fol
    -0.15
    .Packet
    -0.15
    ænd
    -0.15
     itself
    -0.14
    bef
    -0.14
    oras
    -0.14
    POSITIVE LOGITS
     admit
    0.17
    acher
    0.16
    rious
    0.15
    ãĤ¥
    0.14
    rios
    0.14
    RYPT
    0.14
    Integral
    0.14
     RT
    0.14
    ancel
    0.13
     wonder
    0.13
    Act Density 0.048%

    No Known Activations