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

    Neuronpedia

    INDEX
    Explanations

    references to academic concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bree
    -0.18
    UTILITY
    -0.17
    adero
    -0.16
    KeyCode
    -0.15
    deniz
    -0.15
    htar
    -0.15
     racked
    -0.15
    boss
    -0.15
     Leisure
    -0.14
    veloper
    -0.14
    POSITIVE LOGITS
     corpor
    0.24
     Phon
    0.23
     phon
    0.22
     Morph
    0.22
    phon
    0.22
     Romance
    0.22
     morph
    0.21
    morph
    0.21
     Corpor
    0.21
     corpus
    0.21
    Act Density 0.026%

    No Known Activations