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

    Neuronpedia

    INDEX
    Explanations

    proper nouns containing international special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or accented letters in names and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Murdoch
    -0.67
    enegger
    -0.64
     Squid
    -0.64
    ocamp
    -0.64
     almonds
    -0.62
     Matrix
    -0.62
     tentacles
    -0.61
     commercially
    -0.61
     clutch
    -0.60
     stalk
    -0.59
    POSITIVE LOGITS
    ternity
    0.96
    nom
    0.96
    arna
    0.94
    ģ
    0.90
    nai
    0.86
    ivil
    0.85
    ¤
    0.84
    ĥ
    0.84
    û
    0.83
    ĸ
    0.82
    Act Density 0.079%

    No Known Activations