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

    Neuronpedia

    INDEX
    Explanations

    descriptions of things as outstanding or remarkable

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "impressive" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.77
    iche
    -0.71
    sole
    -0.69
    ole
    -0.66
    Rail
    -0.65
    radio
    -0.64
    bid
    -0.63
    othy
    -0.62
    oned
    -0.62
    opter
    -0.62
    POSITIVE LOGITS
     feats
    0.92
     enough
    0.90
     feat
    0.87
     accomplishment
    0.85
    issance
    0.83
     accomplishments
    0.83
     impressive
    0.83
     accol
    0.75
     newcomer
    0.74
    NESS
    0.74
    Act Density 0.014%

    No Known Activations