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

    Neuronpedia

    INDEX
    Explanations

    expressions of criticism towards social structures and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aka
    -0.17
     secs
    -0.14
    fabs
    -0.14
    odb
    -0.14
    åĨµ
    -0.13
     FREE
    -0.13
    oster
    -0.13
     dbl
    -0.13
     FETCH
    -0.13
     reportedly
    -0.13
    POSITIVE LOGITS
     tumblr
    0.16
     *
    0.15
    etty
    0.15
    [^
    0.15
     sorts
    0.15
     ÑĪÑĤÑĥ
    0.15
    Iter
    0.14
    things
    0.14
     XK
    0.14
    WithName
    0.14
    Act Density 4.050%

    No Known Activations