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

    Neuronpedia

    INDEX
    Explanations

    elements related to organization and structural alignment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    963
    -0.18
    ifax
    -0.16
    ESCO
    -0.15
    SRC
    -0.15
    CKER
    -0.15
    ILITY
    -0.14
    OUS
    -0.14
     trú
    -0.14
    EFA
    -0.14
    _REAL
    -0.14
    POSITIVE LOGITS
    angel
    0.17
    asal
    0.15
    ĤŃ
    0.14
     drop
    0.14
    wor
    0.14
    REW
    0.14
     penetration
    0.14
    ylon
    0.14
    drop
    0.14
     worse
    0.14
    Act Density 0.005%

    No Known Activations