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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific validation and measurement accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Internal
    -0.16
     INTERNAL
    -0.15
    INTERNAL
    -0.15
    ungi
    -0.14
     financial
    -0.13
     Mental
    -0.13
    ê·ł
    -0.13
    initely
    -0.13
     finans
    -0.13
     internals
    -0.12
    POSITIVE LOGITS
     empir
    0.36
     experiment
    0.36
     qual
    0.30
     quant
    0.30
    emp
    0.29
     theoretically
    0.28
    experiment
    0.26
     math
    0.26
     comput
    0.25
     mechan
    0.25
    Act Density 0.206%

    No Known Activations