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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intentions or actions to assist others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odd
    -0.16
    ixe
    -0.15
    ellar
    -0.15
    izzo
    -0.14
    asto
    -0.14
    积
    -0.14
    ksam
    -0.14
    axon
    -0.14
    zá
    -0.14
    (éĩij
    -0.14
    POSITIVE LOGITS
    764
    0.16
    缼
    0.15
    rien
    0.14
    ecd
    0.14
    (er
    0.14
    raki
    0.14
    ³
    0.14
    964
    0.13
     syndrome
    0.13
     Syndrome
    0.13
    Act Density 0.011%

    No Known Activations