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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or unexpected outcomes

    oai_token-act-pair · gpt-3.5-turbo

    the word "even" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffen
    -0.90
    aim
    -0.88
    isen
    -0.85
    rend
    -0.83
    Ĥİ
    -0.82
    idelines
    -0.81
    ierrez
    -0.80
    rition
    -0.79
    acker
    -0.78
    ayers
    -0.78
    POSITIVE LOGITS
     remotely
    0.90
     though
    0.82
     outright
    0.78
    handedly
    0.76
     stranger
    0.76
     worse
    0.75
     tho
    0.69
     paran
    0.67
     downright
    0.67
    monary
    0.64
    Act Density 0.059%

    No Known Activations