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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey comparisons or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cad
    -0.16
     Ñģам
    -0.15
    rega
    -0.15
    mage
    -0.14
    tdown
    -0.14
     Bare
    -0.14
    bic
    -0.14
     shar
    -0.13
     bic
    -0.13
    haus
    -0.13
    POSITIVE LOGITS
    æī£
    0.15
    yang
    0.15
     conscient
    0.15
    AdapterFactory
    0.14
    MBED
    0.14
    oust
    0.14
     Neal
    0.14
    uy
    0.13
    gro
    0.13
    ÑģÑĤÑİ
    0.13
    Act Density 0.312%

    No Known Activations