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

    Neuronpedia

    INDEX
    Explanations

    descriptions of conditions or qualities

    oai_token-act-pair · gpt-3.5-turbo

    statements about conditions, particularly those that involve the verbs "was" and "are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     centr
    -0.66
     laure
    -0.65
    anu
    -0.65
     Founding
    -0.63
    isy
    -0.62
     Kickstarter
    -0.62
    backer
    -0.61
    =-=-
    -0.61
     yacht
    -0.60
     signings
    -0.60
    POSITIVE LOGITS
     indistinguishable
    1.10
     resemble
    0.96
     markedly
    0.92
     distinctly
    0.88
     noticeably
    0.87
     decidedly
    0.84
     resembled
    0.82
     strikingly
    0.82
     vastly
    0.81
     identical
    0.81
    Act Density 0.700%

    No Known Activations