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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political matters

    oai_token-act-pair · gpt-3.5-turbo

    references to rights and governance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonetheless
    -0.66
     undoubtedly
    -0.63
     Techniques
    -0.59
     fortunately
    -0.57
     understandably
    -0.55
     definitely
    -0.54
     certainly
    -0.53
     indeed
    -0.53
     tremendously
    -0.53
     doubtless
    -0.53
    POSITIVE LOGITS
    thood
    0.70
    adish
    0.65
     civilisation
    0.64
    animate
    0.60
    livion
    0.58
    ruction
    0.58
    tein
    0.57
    Ò
    0.56
    £ı
    0.56
    vironment
    0.55
    Act Density 1.144%

    No Known Activations