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

    Neuronpedia

    INDEX
    Explanations

    error-related terms or mentions of problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogie
    -0.17
    ecimal
    -0.17
    edii
    -0.17
    ottes
    -0.16
    ed
    -0.16
    oog
    -0.16
    ooth
    -0.15
    eses
    -0.15
    weis
    -0.15
    olle
    -0.15
    POSITIVE LOGITS
    rr
    0.26
    r
    0.25
    ant
    0.23
    ort
    0.23
    ington
    0.22
    one
    0.22
    inger
    0.21
    orm
    0.20
    ror
    0.20
    RR
    0.19
    Act Density 0.017%

    No Known Activations