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

    Neuronpedia

    INDEX
    Explanations

    concepts related to measurement and quantitative analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     soon
    -0.13
    elow
    -0.13
    soon
    -0.12
    orough
    -0.12
    IGO
    -0.12
    ãģ¾ãģ¾
    -0.12
     before
    -0.12
     promptly
    -0.12
    ’Ñıз
    -0.12
    ãģ«ãĤĪ
    -0.12
    POSITIVE LOGITS
     internally
    0.34
     externally
    0.32
    intern
    0.29
    extern
    0.28
    Intern
    0.27
     Intern
    0.26
     physically
    0.26
     technically
    0.26
    Extern
    0.25
     individually
    0.24
    Act Density 0.024%

    No Known Activations