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

    Neuronpedia

    INDEX
    Explanations

    complex phrases that express nuances of human imperfection and ethical dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tual
    -0.16
    igger
    -0.15
    vier
    -0.15
    çe
    -0.15
    ngr
    -0.15
    oul
    -0.14
    etten
    -0.14
    specifier
    -0.14
     atleast
    -0.14
    eydi
    -0.14
    POSITIVE LOGITS
     nor
    0.24
     EVER
    0.19
     anymore
    0.19
     anytime
    0.19
     anyone
    0.17
     anybody
    0.17
     anywhere
    0.16
    .setViewport
    0.16
     anything
    0.15
     NOR
    0.15
    Act Density 0.162%

    No Known Activations