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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparisons and distinctions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hubby
    -0.15
    ney
    -0.15
    ãĥ¼ãĥ©
    -0.14
    pery
    -0.14
    adge
    -0.14
    ä¼ı
    -0.14
    adic
    -0.13
    minus
    -0.13
     indx
    -0.13
     minus
    -0.13
    POSITIVE LOGITS
     TODO
    0.17
    zimmer
    0.15
    TODO
    0.15
    Ä
    0.15
    FIXME
    0.14
     embar
    0.14
     FIXME
    0.13
    ogh
    0.13
    iet
    0.13
    BN
    0.13
    Act Density 0.015%

    No Known Activations