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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and expressions of personal experience or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outh
    -0.16
    uter
    -0.15
    elder
    -0.14
    .unregister
    -0.14
    anmar
    -0.14
    enschaft
    -0.14
     tú
    -0.14
    umes
    -0.14
     UObject
    -0.14
    ome
    -0.13
    POSITIVE LOGITS
     believe
    0.16
     often
    0.15
    etimes
    0.15
     observation
    0.15
    074
    0.15
     wanted
    0.14
    anness
    0.14
     delim
    0.14
    036
    0.14
    legg
    0.14
    Act Density 0.207%

    No Known Activations