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

    Neuronpedia

    INDEX
    Explanations

    references to cognitive and physical entities, especially in the context of group agreements or collective understandings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CONSIN
    -0.66
    jooq
    -0.60
     Ino
    -0.60
    cault
    -0.58
    CRIPT
    -0.58
     defaultstate
    -0.58
    ValueStyle
    -0.57
    WithMany
    -0.57
    XmlAccessType
    -0.57
     cay
    -0.56
    POSITIVE LOGITS
     heads
    1.71
     minds
    1.63
    Heads
    1.58
     hearts
    1.57
     Heads
    1.50
     mouths
    1.46
     bodies
    1.32
     Minds
    1.30
     souls
    1.29
     necks
    1.27
    Act Density 0.164%

    No Known Activations