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

    Neuronpedia

    INDEX
    Explanations

    citation formats or numerical references in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acre
    -0.18
    hist
    -0.15
    lass
    -0.15
    aste
    -0.14
     steril
    -0.14
    iate
    -0.14
     Hub
    -0.14
    ule
    -0.14
     hist
    -0.14
    est
    -0.13
    POSITIVE LOGITS
     flight
    0.16
    afx
    0.16
    ãģĵãģĿ
    0.15
    antha
    0.15
     GOODMAN
    0.15
    usch
    0.14
    pto
    0.14
    ctp
    0.14
    afone
    0.14
     Flight
    0.14
    Act Density 0.000%

    No Known Activations