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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions related to feelings and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     figure
    -0.16
    unos
    -0.16
    itals
    -0.16
    ../../../
    -0.15
    otos
    -0.15
    LETTE
    -0.15
    olas
    -0.15
    esian
    -0.14
    anje
    -0.14
    oler
    -0.14
    POSITIVE LOGITS
    lessly
    0.25
    -good
    0.22
    inspace
    0.21
    ings
    0.20
     sorry
    0.20
     Sorry
    0.19
    thy
    0.18
    sorry
    0.17
    Sorry
    0.16
    inkel
    0.16
    Act Density 0.051%

    No Known Activations