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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in different contexts and variations

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azines
    -0.79
    rador
    -0.75
     monop
    -0.75
     Palestin
    -0.70
    ilver
    -0.67
     confir
    -0.66
     pedigree
    -0.66
     prefrontal
    -0.64
     referen
    -0.63
     glide
    -0.62
    POSITIVE LOGITS
    yond
    1.44
    arers
    1.18
    arer
    1.13
    FORE
    1.08
    cker
    1.06
    zos
    0.98
    ards
    0.95
    gotten
    0.94
    ardless
    0.94
    ek
    0.91
    Act Density 0.012%

    No Known Activations