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

    Neuronpedia

    INDEX
    Explanations

    words related to change and development in a positive context

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belief or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yles
    -0.65
     mentions
    -0.64
     airs
    -0.64
    icles
    -0.63
     Pict
    -0.63
    oop
    -0.60
     Saud
    -0.60
     Brune
    -0.60
     freezes
    -0.58
     camer
    -0.58
    POSITIVE LOGITS
     underestimated
    1.15
     underest
    1.04
     underestimate
    1.03
     overest
    0.97
     overdue
    0.84
    NetMessage
    0.84
     warranted
    0.82
     overlooked
    0.82
     indeed
    0.82
     misunderstood
    0.80
    Act Density 0.648%

    No Known Activations