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

    Neuronpedia

    INDEX
    Explanations

    terms related to quantification and measurement in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indre
    -0.18
    ponent
    -0.17
    ture
    -0.15
    herits
    -0.15
    xls
    -0.14
     Eb
    -0.14
    ullet
    -0.14
    ãĤħ
    -0.14
    irting
    -0.14
    ths
    -0.14
    POSITIVE LOGITS
    itative
    0.33
    ifiable
    0.32
    ifying
    0.31
    ified
    0.30
    ification
    0.30
    ized
    0.28
    ization
    0.28
    itat
    0.27
    itate
    0.26
    itation
    0.25
    Act Density 0.005%

    No Known Activations