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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by a possessive pronoun

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal connections and social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bourg
    -0.68
    Ø©
    -0.68
    bold
    -0.64
    00200000
    -0.64
    ateral
    -0.62
    ngth
    -0.62
    ;;;;;;;;;;;;
    -0.61
    mobi
    -0.61
    <?
    -0.61
    ilitary
    -0.61
    POSITIVE LOGITS
     arrived
    0.79
     slightest
    0.77
     resumed
    0.69
     arrives
    0.68
    steen
    0.68
    roup
    0.68
     coincided
    0.66
     teamed
    0.66
     came
    0.65
     happened
    0.65
    Act Density 0.178%

    No Known Activations