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

    Neuronpedia

    INDEX
    Explanations

    assertive statements about existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erm
    -0.17
    vably
    -0.16
    xbf
    -0.15
    .are
    -0.15
    LIK
    -0.14
    been
    -0.14
     merak
    -0.14
     Ùĩست
    -0.14
    ATEGORIES
    -0.14
     erotique
    -0.14
    POSITIVE LOGITS
     perhaps
    0.17
     so
    0.16
     Something
    0.16
     Hack
    0.15
    Something
    0.15
     din
    0.15
     Perhaps
    0.15
     provided
    0.14
     something
    0.14
    ibir
    0.14
    Act Density 0.074%

    No Known Activations