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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political or governmental events

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of" indicating relationships or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.63
    ucci
    -0.61
     pestic
    -0.58
    allery
    -0.57
     reperto
    -0.55
    culosis
    -0.55
     istg
    -0.52
     predec
    -0.52
    <?
    -0.52
    helle
    -0.52
    POSITIVE LOGITS
     course
    0.84
     sorts
    0.78
    icial
    0.69
    course
    0.65
     JUSTICE
    0.58
     Darkness
    0.57
     ours
    0.55
    sky
    0.52
     theirs
    0.52
     the
    0.51
    Act Density 0.860%

    No Known Activations