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

    Neuronpedia

    INDEX
    Explanations

    phrases that express subjective evaluations or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bergen
    -0.15
     hypoc
    -0.14
    oeff
    -0.14
    ulin
    -0.14
    eland
    -0.14
     odpowied
    -0.13
    iske
    -0.13
    .twitch
    -0.13
    rid
    -0.13
    _um
    -0.12
    POSITIVE LOGITS
     pure
    0.22
    tant
    0.18
     Pure
    0.18
    Pure
    0.18
     yet
    0.18
     sheer
    0.17
     akin
    0.17
     PURE
    0.17
     wish
    0.17
     Exhibit
    0.16
    Act Density 0.307%

    No Known Activations