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

    Neuronpedia

    INDEX
    Explanations

    pronouns and personal references within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOPT
    -0.17
    orado
    -0.16
    drž
    -0.16
    oÅĻ
    -0.15
     chân
    -0.15
    379
    -0.14
    .ws
    -0.14
    Ñıн
    -0.14
    oggler
    -0.14
    ILER
    -0.14
    POSITIVE LOGITS
    ijn
    0.17
     cop
    0.15
    spath
    0.14
    vig
    0.14
     mate
    0.14
    aced
    0.14
    levard
    0.13
    sj
    0.13
    zig
    0.13
     emerg
    0.13
    Act Density 0.164%

    No Known Activations