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

    Neuronpedia

    INDEX
    Explanations

    words related to German language and terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "für" and its variations in German text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.94
    ega
    -0.93
    eros
    -0.88
    eter
    -0.85
    emaker
    -0.84
    esses
    -0.81
    eah
    -0.80
    Bee
    -0.80
    eries
    -0.80
    Boo
    -0.78
    POSITIVE LOGITS
    Downloadha
    0.84
    gency
    0.83
     SIG
    0.72
    ãĥī
    0.69
    senal
    0.67
    ETHOD
    0.66
    geon
    0.63
    ãĤ¢
    0.62
    Interstitial
    0.62
    izont
    0.62
    Act Density 0.040%

    No Known Activations