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

    Neuronpedia

    INDEX
    Explanations

    references to the publication or release of written works or events in specific fields or industries

    oai_token-act-pair · gpt-3.5-turbo

    citations and references in academic or formal texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reated
    -0.71
    oner
    -0.70
    izen
    -0.68
    addons
    -0.68
     choke
    -0.67
    ase
    -0.65
    odes
    -0.63
    comings
    -0.63
    Delete
    -0.63
    ire
    -0.62
    POSITIVE LOGITS
     although
    1.15
     whereas
    1.13
     but
    0.93
     except
    0.87
     according
    0.87
     meaning
    0.86
     supplemented
    0.86
     though
    0.85
     which
    0.85
     namely
    0.85
    Act Density 0.408%

    No Known Activations