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

    Neuronpedia

    INDEX
    Explanations

    words related to permissions and legal authorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugu
    -0.07
    -java
    -0.07
    ibold
    -0.07
    /Foundation
    -0.07
     PureComponent
    -0.07
    edImage
    -0.07
    ileceÄŁini
    -0.07
    ilece
    -0.07
    θεÏģ
    -0.07
    unga
    -0.07
    POSITIVE LOGITS
     use
    0.08
    bie
    0.06
    lah
    0.06
     stra
    0.06
    -AA
    0.06
     only
    0.06
     us
    0.05
    .truth
    0.05
    äch
    0.05
    epad
    0.05
    Act Density 0.015%

    No Known Activations