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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atis
    -0.86
    ĸļ
    -0.80
    selage
    -0.79
    unciation
    -0.79
    hof
    -0.78
    orno
    -0.76
    onom
    -0.75
    ortmund
    -0.74
    oris
    -0.74
    orius
    -0.71
    POSITIVE LOGITS
    dating
    1.03
    coming
    0.84
    stairs
    0.81
    ban
    0.80
    ward
    0.79
    bone
    0.77
    ded
    0.76
    side
    0.76
    lishes
    0.76
    dit
    0.75
    Act Density 0.008%

    No Known Activations