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

    Neuronpedia

    INDEX
    Explanations

    terms related to assistance and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idious
    -0.18
    they
    -0.17
    she
    -0.15
    aks
    -0.15
    elyn
    -0.14
    uml
    -0.14
    yet
    -0.14
    lam
    -0.14
    aviest
    -0.14
     voks
    -0.13
    POSITIVE LOGITS
     the
    0.31
     them
    0.26
     a
    0.26
     your
    0.25
     those
    0.21
     their
    0.21
     some
    0.21
     an
    0.20
     its
    0.20
     these
    0.19
    Act Density 0.586%

    No Known Activations