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

    Neuronpedia

    INDEX
    Explanations

    expressions related to writing and authoring experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .decode
    -0.14
    infeld
    -0.14
     خرد
    -0.14
    ackson
    -0.13
    Decode
    -0.13
    VD
    -0.13
    Äħż
    -0.13
    alles
    -0.13
    xn
    -0.13
    aga
    -0.13
    POSITIVE LOGITS
     Writing
    0.31
     writing
    0.29
     Writer
    0.29
     Writers
    0.29
     writers
    0.28
    writing
    0.27
    Writing
    0.25
    writers
    0.25
    -writing
    0.24
     writer
    0.24
    Act Density 0.270%

    No Known Activations