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

    Neuronpedia

    INDEX
    Explanations

    word pairs or phrases connected by "and"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the conjunction "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.60
     Abbey
    -0.55
    SPONSORED
    -0.55
    zynski
    -0.54
     banner
    -0.54
     marginal
    -0.54
     Santana
    -0.53
    ¥ŀ
    -0.53
     Penal
    -0.52
     Plaza
    -0.52
    POSITIVE LOGITS
    tenance
    0.96
    etheless
    0.94
    usterity
    0.91
    lihood
    0.88
    _
    0.88
    -
    0.88
    xiety
    0.88
    -$
    0.84
    terday
    0.83
    alog
    0.82
    Act Density 0.150%

    No Known Activations