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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating disagreement or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.16
    odont
    -0.15
    IRO
    -0.15
    iro
    -0.14
    ilk
    -0.13
    mess
    -0.13
    ikan
    -0.13
    ilib
    -0.13
    ’aut
    -0.13
    opsis
    -0.13
    POSITIVE LOGITS
     itself
    0.20
     its
    0.18
    urbed
    0.17
    unes
    0.16
     Its
    0.16
     own
    0.15
    erot
    0.15
    lef
    0.14
    Its
    0.14
    sum
    0.14
    Act Density 0.227%

    No Known Activations