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

    Neuronpedia

    INDEX
    Explanations

    text relating to questions or queries

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific symbol or character combination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.77
    bda
    -0.63
    Buyable
    -0.60
     unmarked
    -0.58
     mosqu
    -0.58
     Mobil
    -0.58
     plaster
    -0.57
     Tanz
    -0.55
     Colleg
    -0.55
    çĶ°
    -0.55
    POSITIVE LOGITS
    ¹
    0.85
    you
    0.82
    they
    0.81
    ¡
    0.80
    ought
    0.79
    ı
    0.78
    else
    0.77
    eenth
    0.77
    ¬
    0.77
    º
    0.76
    Act Density 0.066%

    No Known Activations