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 indicating contrast or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rend
    -1.07
    aim
    -0.79
    asus
    -0.79
    othy
    -0.76
    cel
    -0.74
    idem
    -0.72
    ahime
    -0.71
    obi
    -0.70
    ========
    -0.69
    idelines
    -0.69
    POSITIVE LOGITS
     remotely
    1.02
     though
    1.01
     tho
    0.91
     stranger
    0.65
     moderately
    0.65
    handedly
    0.64
     worse
    0.64
    handed
    0.63
     mentioning
    0.63
     paran
    0.63
    Act Density 0.064%

    No Known Activations