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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a critical opinion or judgement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey the concept of understanding or clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lens
    -0.66
    amiya
    -0.63
    CRE
    -0.63
    Aff
    -0.61
     stewards
    -0.59
    meet
    -0.57
    sha
    -0.57
    rifice
    -0.55
     retri
    -0.55
     Presence
    -0.55
    POSITIVE LOGITS
     drift
    0.87
     gist
    0.81
     twisted
    0.73
     vibe
    0.72
    chy
    0.70
    ©¶æ
    0.66
    oglu
    0.66
     impression
    0.66
    patrick
    0.64
     feeling
    0.63
    Act Density 0.148%

    No Known Activations