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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.70
     
    -0.66
    ,
    -0.66
     L
    -0.65
     e
    -0.64
     P
    -0.63
     R
    -0.62
     heart
    -0.62
    -
    -0.62
     H
    -0.60
    POSITIVE LOGITS
     myſelf
    1.17
     Efq
    1.15
     doubtnut
    1.12
     Theſe
    1.10
     مرئيه
    1.07
     BoxFit
    1.01
     Monfieur
    1.01
    berdayakan
    1.01
     itſelf
    1.00
     تانيه
    0.99
    Act Density 0.438%

    No Known Activations