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

    Neuronpedia

    INDEX
    Explanations

    expressions related to emotions and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otos
    -0.16
    anje
    -0.16
    cai
    -0.15
    ../../../
    -0.15
    itals
    -0.15
     figure
    -0.15
    unos
    -0.15
    λοÏħ
    -0.15
    unidad
    -0.15
    esian
    -0.14
    POSITIVE LOGITS
     sorry
    0.21
    lessly
    0.20
    ings
    0.19
    -good
    0.19
    thy
    0.18
     Sorry
    0.17
    inspace
    0.17
    sorry
    0.17
    ledged
    0.16
    ald
    0.16
    Act Density 0.051%

    No Known Activations