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

    Neuronpedia

    INDEX
    Explanations

    terms related to inspection and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agal
    -0.17
    uhn
    -0.15
    ramework
    -0.15
    osta
    -0.14
    les
    -0.13
    arrant
    -0.13
    ennis
    -0.13
    ock
    -0.13
     McN
    -0.13
    Äį
    -0.13
    POSITIVE LOGITS
    arness
    0.16
     Rhodes
    0.15
     ç¯
    0.15
    akov
    0.14
    ÑĥеÑĤ
    0.14
    IOC
    0.14
    å»
    0.14
    ertia
    0.13
     rh
    0.13
     Lev
    0.13
    Act Density 0.320%

    No Known Activations