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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to emotional experiences and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enheim
    -0.16
     trh
    -0.15
     [
    -0.14
    vor
    -0.14
     disap
    -0.14
    hsi
    -0.13
    028
    -0.13
    ansom
    -0.13
    RESSION
    -0.13
    ↵↵
    -0.13
    POSITIVE LOGITS
    .Dom
    0.28
     programme
    0.14
    ,...
    0.14
     cunt
    0.14
     Programme
    0.13
     programmes
    0.13
    >%
    0.13
     Wich
    0.13
     `.
    0.13
    оÐ
    0.13
    Act Density 0.093%

    No Known Activations