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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional relationships or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suce
    -0.20
    StateChanged
    -0.15
    кÑĥл
    -0.15
    cctor
    -0.15
    slaught
    -0.14
    .BLL
    -0.14
    enstein
    -0.14
    ÙĨتÛĮ
    -0.14
    .Apis
    -0.14
    à¤ķन
    -0.13
    POSITIVE LOGITS
    711
    0.15
     Julio
    0.15
    ABCDEFGHIJKLMNOP
    0.14
    ahlen
    0.14
    457
    0.14
    tip
    0.14
    çĬ¶
    0.14
    ally
    0.14
    tel
    0.14
    ure
    0.14
    Act Density 0.425%

    No Known Activations