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

    Neuronpedia

    INDEX
    Explanations

    terms related to observation and descriptive analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spiel
    -0.18
    isle
    -0.17
    atever
    -0.16
    yen
    -0.16
    ped
    -0.16
    ãģ°
    -0.15
    loe
    -0.14
    .AutoScaleMode
    -0.14
     Tester
    -0.14
    -legged
    -0.14
    POSITIVE LOGITS
    tower
    0.22
    à¸ģารà¸ĵ
    0.22
    vation
    0.21
    å¯Ł
    0.20
    /me
    0.20
    ably
    0.20
    erved
    0.18
     closely
    0.18
    /report
    0.17
    (obs
    0.17
    Act Density 0.032%

    No Known Activations