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

    Neuronpedia

    INDEX
    Explanations

    references to investigative journalism and reporting practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grids
    -0.15
    owski
    -0.15
    rag
    -0.14
    965
    -0.14
    umbn
    -0.14
    ittel
    -0.14
    jang
    -0.14
    quin
    -0.13
    vä
    -0.13
    asa
    -0.13
    POSITIVE LOGITS
     exposes
    0.30
     expose
    0.30
     investigative
    0.29
     expos
    0.27
     exposed
    0.26
     investigation
    0.26
     investigations
    0.24
     exposures
    0.24
     exposing
    0.24
     investig
    0.23
    Act Density 0.124%

    No Known Activations