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

    Neuronpedia

    INDEX
    Explanations

    prepositions and pronouns in phrases describing actions and relationships between individuals

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and conjunctions related to relationships and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cedented
    -0.77
    exempt
    -0.76
    isphere
    -0.74
    ancial
    -0.71
    âķIJ
    -0.70
    olutions
    -0.69
     redes
    -0.68
    documented
    -0.67
    Interstitial
    -0.67
    chnology
    -0.67
    POSITIVE LOGITS
     Luffy
    1.26
     Jaune
    1.22
     Pyrrha
    1.22
     Hermione
    1.20
     Snape
    1.15
     Shinji
    1.14
     Goku
    1.14
     Zhou
    1.13
     Malfoy
    1.13
     Draco
    1.13
    Act Density 0.777%

    No Known Activations