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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to the contrary."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Controlled
    -0.73
    killer
    -0.70
     Cars
    -0.69
    lic
    -0.66
     Survivor
    -0.65
    edu
    -0.64
    rien
    -0.64
    liam
    -0.64
    aus
    -0.63
     Elvis
    -0.63
    POSITIVE LOGITS
    etheless
    0.82
     contrary
    0.78
     notwithstanding
    0.75
    mentioned
    0.72
     minded
    0.72
     guiActiveUn
    0.67
    ptions
    0.66
     imply
    0.65
     ende
    0.60
    yet
    0.60
    Act Density 0.020%

    No Known Activations