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

    Neuronpedia

    INDEX
    Explanations

    keywords associated with abilities or skills

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to capabilities or skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roman
    -0.67
     Surv
    -0.65
    enegger
    -0.63
    agar
    -0.63
    algia
    -0.62
     Tags
    -0.62
     Parents
    -0.62
    raining
    -0.62
     Observ
    -0.62
     1943
    -0.61
    POSITIVE LOGITS
    Reviewer
    0.88
    ibility
    0.87
    bodied
    0.86
    auga
    0.84
    ibilities
    0.82
    Ability
    0.82
     impaired
    0.77
     ability
    0.74
    llor
    0.73
    ioned
    0.73
    Act Density 0.041%

    No Known Activations