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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "used" alongside descriptive phrases indicating functionalities or applications of concepts, particularly in a charitable or beneficial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inos
    -0.14
    830
    -0.14
    alam
    -0.14
    UDA
    -0.14
    prov
    -0.14
    ampp
    -0.13
    adal
    -0.13
    ivos
    -0.13
     prejudice
    -0.13
    cheng
    -0.13
    POSITIVE LOGITS
     tool
    0.19
    source
    0.16
     sunk
    0.16
    Sink
    0.16
    ISCO
    0.15
     sink
    0.15
     source
    0.15
    orns
    0.15
    sink
    0.15
    prü
    0.15
    Act Density 0.124%

    No Known Activations