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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "Se" or similar variations, likely indicating a focus on specific named entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.17
    loc
    -0.17
    sec
    -0.17
    thers
    -0.17
    ser
    -0.16
    ì§Ŀ
    -0.15
    lob
    -0.15
    lla
    -0.15
    ovy
    -0.15
    log
    -0.15
    POSITIVE LOGITS
    bastian
    0.26
    bast
    0.23
    vere
    0.22
    ATTLE
    0.22
    attle
    0.21
    amus
    0.21
    infeld
    0.21
    attles
    0.19
    jour
    0.19
    ismic
    0.18
    Act Density 0.024%

    No Known Activations