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

    Neuronpedia

    INDEX
    Explanations

    names of people or places ending with "je"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "je" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.76
    izoph
    -0.73
    moving
    -0.72
    DERR
    -0.68
    grounds
    -0.68
    reads
    -0.67
    imates
    -0.67
    ingham
    -0.66
    norm
    -0.66
    speak
    -0.66
    POSITIVE LOGITS
    lde
    1.03
    je
    0.99
    Å¡
    0.97
    anwhile
    0.93
    eling
    0.91
    orge
    0.87
    opard
    0.86
    lda
    0.84
    cki
    0.84
    ansson
    0.83
    Act Density 0.008%

    No Known Activations