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

    Neuronpedia

    INDEX
    Explanations

    patterns and feelings of discovery or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lag
    -0.17
    emann
    -0.16
     drawn
    -0.15
    лага
    -0.15
    _alignment
    -0.14
    lm
    -0.14
    åıĤ
    -0.13
    IGN
    -0.13
    UNKNOWN
    -0.13
    ãĥ³ãĥģ
    -0.13
    POSITIVE LOGITS
    esy
    0.17
    ensburg
    0.17
    .synthetic
    0.16
    Ð¡Ðł
    0.15
    attern
    0.14
    æ§
    0.14
     Balls
    0.14
    ziej
    0.14
    edList
    0.13
    zburg
    0.13
    Act Density 0.216%

    No Known Activations