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

    Neuronpedia

    INDEX
    Explanations

    patterns in repetitions of symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or repeated symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Writ
    -0.64
    Deb
    -0.59
     veget
    -0.57
    AUD
    -0.56
     sponsoring
    -0.55
     orchestr
    -0.55
     supportive
    -0.55
    intent
    -0.54
    lav
    -0.54
     interpret
    -0.54
    POSITIVE LOGITS
     istg
    0.77
     ..............
    0.71
    ]);
    0.69
    train
    0.65
    ]).
    0.63
    Train
    0.62
     ................
    0.61
     ..
    0.61
     ......
    0.61
     Frieza
    0.61
    Act Density 0.202%

    No Known Activations