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

    Neuronpedia

    INDEX
    Explanations

    references to people's opinions and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cannot
    -0.16
     Cannot
    -0.16
    _Tis
    -0.15
    ãĤ¤ãĥ³ãĥĪ
    -0.15
    cannot
    -0.15
     Ùĩا
    -0.15
    %S
    -0.14
    \core
    -0.13
    ìĿ¸ê°Ģ
    -0.13
    fec
    -0.13
    POSITIVE LOGITS
    're
    0.42
    ’re
    0.40
    've
    0.37
    'll
    0.36
    ’ve
    0.35
    ’ll
    0.34
    'd
    0.32
    'm
    0.31
    ’d
    0.29
    ’m
    0.29
    Act Density 0.527%

    No Known Activations