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

    Neuronpedia

    INDEX
    Explanations

    foreign language words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols used in formatting or representing languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettings
    -0.81
    izable
    -0.74
    bart
    -0.65
    Assembly
    -0.63
    anwhile
    -0.63
     bearer
    -0.62
    ifications
    -0.60
     tickets
    -0.59
     surprises
    -0.59
    itarian
    -0.59
    POSITIVE LOGITS
    ¹
    1.62
    ĸ
    1.58
    ħ
    1.58
    Ķ
    1.58
    ·
    1.51
    Į
    1.50
    ¾
    1.50
    ĺ
    1.49
    Ħ
    1.49
    ľ
    1.48
    Act Density 0.022%

    No Known Activations