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

    Neuronpedia

    INDEX
    Explanations

    patterns related to character names or initials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏħÏĥ
    -0.16
    æ¿
    -0.16
    strap
    -0.16
    éĽ
    -0.15
    jet
    -0.15
    agle
    -0.15
    eldon
    -0.15
    ityEngine
    -0.15
    ious
    -0.14
    J
    -0.14
    POSITIVE LOGITS
    oes
    0.22
    AMES
    0.21
    upyter
    0.21
    alous
    0.21
    oints
    0.21
    inx
    0.20
    ournals
    0.19
    ockey
    0.18
    udd
    0.18
    aded
    0.18
    Act Density 0.081%

    No Known Activations