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

    Neuronpedia

    INDEX
    Explanations

    references to government or governmental organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apult
    -0.15
    ophobia
    -0.15
    assen
    -0.15
    ding
    -0.14
    031
    -0.14
    nez
    -0.14
    033
    -0.14
     Kostenlos
    -0.13
    241
    -0.13
    ozem
    -0.13
    POSITIVE LOGITS
    wide
    0.20
    ally
    0.17
    ality
    0.17
    al
    0.16
    .LookAndFeel
    0.16
    edList
    0.16
    arians
    0.15
    als
    0.15
    UNDLE
    0.15
    èles
    0.14
    Act Density 0.052%

    No Known Activations