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

    Neuronpedia

    INDEX
    Explanations

    references to shipwrecks and maritime disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kre
    -0.16
    pler
    -0.15
    iverse
    -0.15
    ative
    -0.15
     Provid
    -0.14
     Moss
    -0.14
     Ducks
    -0.14
    ãĤ¤ãĤ¯
    -0.14
    atura
    -0.14
     Jes
    -0.14
    POSITIVE LOGITS
     доÑĤ
    0.16
    ghi
    0.15
    ĽĪ
    0.15
    itet
    0.14
    illos
    0.14
    FFFFFFFF
    0.14
     Broad
    0.14
    fat
    0.13
    sar
    0.13
    cur
    0.13
    Act Density 0.023%

    No Known Activations