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

    Neuronpedia

    INDEX
    Explanations

    significant actions or events happening or being decided

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to announcements and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iolet
    -0.70
    onga
    -0.61
    ãĥĺ
    -0.58
    adow
    -0.58
     brill
    -0.58
    imble
    -0.54
    iaries
    -0.54
    hire
    -0.53
    ao
    -0.53
     practition
    -0.53
    POSITIVE LOGITS
     anew
    0.99
    liest
    0.94
    ultimate
    0.92
    iest
    0.89
    same
    0.80
     correctly
    0.74
    osphere
    0.71
    hest
    0.70
     anonymously
    0.70
     closest
    0.65
    Act Density 0.374%

    No Known Activations