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

    Neuronpedia

    INDEX
    Explanations

    statements that provide emphasis on the importance of certain information or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owe
    -0.73
    bryce
    -0.70
    rose
    -0.65
    uron
    -0.65
    ramids
    -0.64
    chairs
    -0.64
    boro
    -0.63
    alk
    -0.63
    alter
    -0.62
    anchester
    -0.62
    POSITIVE LOGITS
     however
    0.92
     though
    0.79
     namely
    0.75
     moreover
    0.75
     insofar
    0.68
     besides
    0.66
     alas
    0.65
     albeit
    0.64
    ÃĤ
    0.64
    SPONSORED
    0.63
    Act Density 0.172%

    No Known Activations