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

    Neuronpedia

    INDEX
    Explanations

    informal conversational phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayne
    -0.18
    orna
    -0.15
    901
    -0.15
    üy
    -0.15
     repay
    -0.15
    stamp
    -0.14
    .stamp
    -0.14
    à¹Ģลย
    -0.13
    operand
    -0.13
    ÏĦÏģ
    -0.13
    POSITIVE LOGITS
     Times
    0.16
     impr
    0.16
    aur
    0.16
    arus
    0.15
    ipped
    0.15
     å§
    0.14
    Times
    0.14
    iston
    0.14
    jon
    0.14
    arent
    0.14
    Act Density 0.093%

    No Known Activations