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

    Neuronpedia

    INDEX
    Explanations

    references to award shows and hosting events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahkan
    -0.15
    ousse
    -0.15
    ãĥŃãĥ¼
    -0.14
    agus
    -0.14
    容
    -0.14
    icus
    -0.14
    icana
    -0.14
    /testing
    -0.14
    iÄį
    -0.14
    Ø´ÛĮ
    -0.14
    POSITIVE LOGITS
    ắt
    0.16
     censor
    0.15
    phere
    0.14
     floor
    0.14
     possession
    0.14
    ungs
    0.14
     Floor
    0.14
    oto
    0.14
    untime
    0.13
     Torrent
    0.13
    Act Density 0.052%

    No Known Activations