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

    Neuronpedia

    INDEX
    Explanations

    elements and terms related to evaluation and decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    462
    -0.17
    fone
    -0.16
     Sac
    -0.15
    912
    -0.15
    597
    -0.15
    ury
    -0.15
    471
    -0.15
    926
    -0.14
    ptype
    -0.14
    504
    -0.13
    POSITIVE LOGITS
    addock
    0.15
    èķ
    0.15
    Å¡t
    0.15
    گز
    0.14
    μιο
    0.14
    §
    0.14
    rust
    0.14
    azor
    0.14
    üt
    0.14
    VO
    0.14
    Act Density 0.004%

    No Known Activations