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

    Neuronpedia

    INDEX
    Explanations

    formats and file types

    oai_token-act-pair · gpt-3.5-turbo

    references to various formats, particularly in a digital context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.85
    yer
    -0.81
    undai
    -0.77
    riv
    -0.74
    rogen
    -0.72
    hood
    -0.72
    ortium
    -0.71
    doms
    -0.70
    akening
    -0.70
    atana
    -0.69
    POSITIVE LOGITS
     format
    1.30
     formats
    1.10
     Format
    1.04
    format
    1.01
    Format
    0.92
     formatted
    0.84
     formatting
    0.79
    ters
    0.79
    atted
    0.78
    FORM
    0.76
    Act Density 0.009%

    No Known Activations