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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Se" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CPC
    -0.70
     diplom
    -0.67
    etheless
    -0.64
     realism
    -0.63
     hemisphere
    -0.61
    INGTON
    -0.61
     Judd
    -0.61
     AFL
    -0.61
     sender
    -0.60
     owl
    -0.60
    POSITIVE LOGITS
    ldom
    1.36
    infeld
    1.31
    vere
    1.26
    gments
    1.24
    xton
    1.21
    gment
    1.19
    eker
    1.19
    amus
    1.16
    gregation
    1.12
    bring
    1.10
    Act Density 0.018%

    No Known Activations