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

    Neuronpedia

    INDEX
    Explanations

    concepts related to measurement and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enium
    -0.82
    vous
    -0.74
     Nero
    -0.70
    apple
    -0.69
    renheit
    -0.68
     Edison
    -0.66
    mud
    -0.65
    odon
    -0.65
    ovie
    -0.64
    enegger
    -0.64
    POSITIVE LOGITS
     considerations
    1.19
     differences
    1.14
     specificity
    1.11
     constraints
    0.96
     adequ
    0.96
     factors
    0.96
     matters
    0.93
     disparities
    0.93
     modifiers
    0.91
     bias
    0.90
    Act Density 0.173%

    No Known Activations