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

    Neuronpedia

    INDEX
    Explanations

    German words containing characters like "ür"

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to locations or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orers
    -0.73
    regor
    -0.71
    orer
    -0.68
    eln
    -0.66
    uncture
    -0.64
    esses
    -0.64
    wright
    -0.62
    arse
    -0.62
    frey
    -0.61
    otent
    -0.60
    POSITIVE LOGITS
    ãĥī
    1.02
    gency
    0.99
    ãĥĹ
    0.84
    ü
    0.83
    geon
    0.81
    ãĥIJ
    0.80
    ãĥĢ
    0.78
    mingham
    0.77
    gew
    0.76
    ãĥĥ
    0.75
    Act Density 0.007%

    No Known Activations