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

    Neuronpedia

    INDEX
    Explanations

    references to themes in literature or art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneous
    -0.20
    ty
    -0.18
    OUR
    -0.17
    teen
    -0.17
    nd
    -0.17
    ude
    -0.16
    nde
    -0.16
     Hayward
    -0.15
    our
    -0.15
    leans
    -0.15
    POSITIVE LOGITS
    æĿIJ
    0.20
    TEGER
    0.18
    eting
    0.18
    ologies
    0.17
    elves
    0.17
    .Tasks
    0.16
    ihn
    0.15
    subst
    0.15
    ienes
    0.15
    atical
    0.15
    Act Density 0.015%

    No Known Activations