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

    Neuronpedia

    INDEX
    Explanations

    references to specific authors, literary works, and themes related to literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ATTRIBUTE
    -0.15
    urette
    -0.15
    urnal
    -0.15
     Siege
    -0.15
     mainland
    -0.15
     Goddess
    -0.14
     hone
    -0.14
    iais
    -0.14
     Invocation
    -0.14
    .defer
    -0.14
    POSITIVE LOGITS
     Dickens
    0.36
    Dick
    0.30
     Eb
    0.25
    Eb
    0.24
     Pip
    0.23
     Dick
    0.22
     Oliver
    0.21
     dick
    0.21
     Mic
    0.21
     Charles
    0.20
    Act Density 0.019%

    No Known Activations