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

    Neuronpedia

    INDEX
    Explanations

    references to past experiences and their impact on relationships and learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bung
    -0.20
     anymore
    -0.16
     Hlav
    -0.16
    quip
    -0.16
    wich
    -0.15
    aman
    -0.15
    ezi
    -0.15
     Affero
    -0.14
    dera
    -0.14
     Tuesday
    -0.13
    POSITIVE LOGITS
     sometimes
    0.26
    sometimes
    0.21
    ’ve
    0.21
     Ive
    0.20
    've
    0.20
     either
    0.19
    ecz
    0.18
     Sometimes
    0.18
    Sometimes
    0.18
    variably
    0.17
    Act Density 0.253%

    No Known Activations