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

    Neuronpedia

    INDEX
    Explanations

    words related to resistance or protection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to resistance or resilience in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPA
    -0.84
    hire
    -0.79
    =-=-=-=-
    -0.78
    raltar
    -0.77
    amen
    -0.74
     largeDownload
    -0.74
    calling
    -0.73
    utra
    -0.72
    EStream
    -0.72
    swick
    -0.72
    POSITIVE LOGITS
     suscept
    0.99
     immunity
    0.85
     resistant
    0.83
     tolerant
    0.80
     immune
    0.79
     adaptive
    0.78
    icide
    0.73
     susceptible
    0.73
     weeds
    0.72
     corrosion
    0.72
    Act Density 0.014%

    No Known Activations