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

    Neuronpedia

    INDEX
    Explanations

    references to popular theories or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    大åħ¨
    -0.08
    åħ¸
    -0.07
     dahi
    -0.07
    Preview
    -0.07
    benchmark
    -0.06
    udad
    -0.06
    (æ°´
    -0.06
    hud
    -0.06
    ocaly
    -0.06
    udit
    -0.06
    POSITIVE LOGITS
     theories
    0.24
     theory
    0.23
     hypothesis
    0.22
     Theory
    0.21
    Theory
    0.19
    theory
    0.18
     hypotheses
    0.18
     THEORY
    0.17
     hypo
    0.15
     possibility
    0.15
    Act Density 0.166%

    No Known Activations