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

    Neuronpedia

    INDEX
    Explanations

    references to hunger or the word "Hunger" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asca
    -0.17
    lear
    -0.16
    ivas
    -0.16
    ogra
    -0.15
    ative
    -0.15
    ãģķãĤĵ
    -0.15
    ampo
    -0.14
    rane
    -0.14
     Separate
    -0.14
     Digest
    -0.14
    POSITIVE LOGITS
     thirst
    0.21
     hunger
    0.20
     Hunger
    0.18
     pains
    0.18
    lust
    0.18
     hungry
    0.17
     satisfied
    0.17
     Games
    0.17
     appetite
    0.17
    igue
    0.16
    Act Density 0.012%

    No Known Activations