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

    Neuronpedia

    INDEX
    Explanations

    adverbs or adjectives used to describe one's personal characteristics or actions in a candid manner

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "openly" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.74
    ifully
    -0.69
     perman
    -0.69
    ocre
    -0.68
    batch
    -0.66
    oday
    -0.65
    ency
    -0.64
    anova
    -0.64
     Millennium
    -0.63
     Landing
    -0.63
    POSITIVE LOGITS
     defied
    0.84
     hostile
    0.82
     defy
    0.81
     bisexual
    0.80
     contradict
    0.79
     contradicted
    0.77
    obin
    0.77
     traded
    0.77
     confront
    0.76
     gay
    0.76
    Act Density 0.052%

    No Known Activations