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

    Neuronpedia

    INDEX
    Explanations

    action phrases related to public actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating public relations or social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilies
    -0.77
    uncture
    -0.71
    ility
    -0.68
    peria
    -0.65
    ilege
    -0.65
    ngth
    -0.64
    isure
    -0.62
    iu
    -0.61
    kus
    -0.61
    nance
    -0.61
    POSITIVE LOGITS
     unnoticed
    0.96
    wagon
    0.75
    bye
    0.75
     downhill
    0.71
    cycle
    0.71
     raft
    0.71
     smoothly
    0.71
     stairs
    0.69
    onda
    0.69
    eper
    0.68
    Act Density 0.116%

    No Known Activations