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

    Neuronpedia

    INDEX
    Explanations

    terms related to computer programming languages

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Pixar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¨
    -0.79
    ANK
    -0.71
    RAW
    -0.65
    #$#$
    -0.63
    INST
    -0.63
    lehem
    -0.63
    udder
    -0.63
     à¨
    -0.62
    à©
    -0.62
    thal
    -0.60
    POSITIVE LOGITS
    xes
    1.17
    edo
    1.09
    xus
    1.04
    eus
    1.00
    es
    0.98
    iang
    0.97
    avier
    0.94
    iao
    0.92
    aminer
    0.89
    posure
    0.86
    Act Density 0.040%

    No Known Activations