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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or significant attributes related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.80
    στημα
    -0.76
    ]<<"
    -0.66
    MessageTagHelper
    -0.61
    ThroughAttribute
    -0.59
     Portail
    -0.58
     Jefus
    -0.57
     pleaſure
    -0.57
     duchess
    -0.57
     themſelves
    -0.56
    POSITIVE LOGITS
     betrekking
    0.75
    Билгалдахарш
    0.72
     become
    0.60
     ISNI
    0.57
     implications
    0.56
    invokeLater
    0.55
     ramifications
    0.54
     been
    0.53
     implica
    0.53
     never
    0.53
    Act Density 0.228%

    No Known Activations