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

    Neuronpedia

    INDEX
    Explanations

    specific characters or characters that constitute a certain pattern

    oai_token-act-pair · gpt-3.5-turbo

    symbols and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dragonbound
    -0.85
    oulos
    -0.73
     resemblance
    -0.71
     resemb
    -0.71
     similarities
    -0.68
     Aston
    -0.66
     omission
    -0.66
     dossier
    -0.66
     similarity
    -0.64
     intrigue
    -0.62
    POSITIVE LOGITS
    ¹
    1.57
    ħ
    1.56
    į
    1.50
    ĭ
    1.50
    ´
    1.49
    ĺ
    1.49
    Ĭ
    1.48
    °
    1.46
    ī
    1.45
    ¸
    1.44
    Act Density 0.022%

    No Known Activations