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

    Neuronpedia

    INDEX
    Explanations

    phrases related to methods of providing help or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allen
    -0.17
    ahat
    -0.15
    reur
    -0.15
     isize
    -0.15
    beat
    -0.14
    uld
    -0.14
    ussen
    -0.14
    uiltin
    -0.14
    ekl
    -0.13
    voj
    -0.13
    POSITIVE LOGITS
    edException
    0.16
    EDI
    0.15
     first
    0.14
    opic
    0.14
    upon
    0.14
    ared
    0.14
    ipe
    0.14
     franc
    0.14
    нед
    0.13
    bone
    0.13
    Act Density 0.075%

    No Known Activations