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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causality or reasoning

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mare
    -0.67
     awaits
    -0.66
    isable
    -0.65
    iaries
    -0.62
    gee
    -0.62
    erer
    -0.62
    iste
    -0.61
     nodd
    -0.60
    uckland
    -0.60
    aire
    -0.59
    POSITIVE LOGITS
     sheer
    0.94
     their
    0.66
     pree
    0.63
    é¾įå¥ij士
    0.63
     luck
    0.63
     course
    0.63
     misunderstand
    0.63
     necessity
    0.62
     obvious
    0.62
     its
    0.61
    Act Density 0.056%

    No Known Activations