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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ix"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or brand related to media, technology, or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lehem
    -0.78
    METHOD
    -0.70
    VEL
    -0.70
    RAW
    -0.68
    #$#$
    -0.67
    è¦ļéĨĴ
    -0.67
    ANK
    -0.66
    riter
    -0.66
    ufact
    -0.66
    GROUND
    -0.65
    POSITIVE LOGITS
    es
    1.16
    edo
    0.91
    ilated
    0.89
    iao
    0.88
    xes
    0.87
    iliary
    0.86
    avier
    0.85
    xus
    0.83
    iang
    0.83
    ercise
    0.81
    Act Density 0.016%

    No Known Activations