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

    Neuronpedia

    INDEX
    Explanations

    components related to data accuracy and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osten
    -0.13
     theories
    -0.13
    -sized
    -0.12
    .responses
    -0.12
    obbies
    -0.11
     Businesses
    -0.11
     sized
    -0.11
    enas
    -0.11
     Abilities
    -0.11
    inn
    -0.11
    POSITIVE LOGITS
     flagged
    0.28
     flags
    0.27
     flag
    0.26
     Flags
    0.24
    flag
    0.23
    -flag
    0.23
     Flag
    0.22
    Flag
    0.21
     QC
    0.21
    flags
    0.21
    Act Density 0.022%

    No Known Activations