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

    Neuronpedia

    INDEX
    Explanations

    references to specific key identifiers or labels in data structures or code

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    roff
    -0.60
     Oj
    -0.57
    AtIndexPath
    -0.56
     Gambit
    -0.54
     keys
    -0.52
     Seder
    -0.52
    Diwedd
    -0.51
     jij
    -0.51
     Arden
    -0.51
     footing
    -0.50
    POSITIVE LOGITS
    Key
    1.87
     Key
    1.09
     Keystone
    0.63
     незавершена
    0.62
    حياتها
    0.61
    蚪
    0.60
    POUND
    0.59
    ThroughAttribute
    0.57
    RetentionPolicy
    0.57
     ComVisible
    0.56
    Act Density 0.002%

    No Known Activations