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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and contractions

    oai_token-act-pair · gpt-3.5-turbo

    personal expressions of uncertainty or inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayer
    -0.73
     hugs
    -0.71
     Decay
    -0.67
     drains
    -0.64
    soDeliveryDate
    -0.64
     Bye
    -0.61
     outgoing
    -0.61
     Slay
    -0.60
     continuation
    -0.60
     Rise
    -0.60
    POSITIVE LOGITS
     verify
    0.98
     substant
    0.94
     discern
    0.90
     doubt
    0.84
     pinpoint
    0.84
     verified
    0.84
     corrobor
    0.84
     detect
    0.83
     ascert
    0.83
     find
    0.83
    Act Density 0.207%

    No Known Activations