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

    Neuronpedia

    INDEX
    Explanations

    terms related to effectiveness and efficiency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ver
    -0.53
    Scho
    -0.50
     Ver
    -0.50
     gost
    -0.47
    ざ
    -0.47
    ार्
    -0.44
    I
    -0.43
     affect
    -0.42
     I
    -0.42
    Expedia
    -0.41
    POSITIVE LOGITS
     itſelf
    1.07
     Efq
    1.05
     Houſe
    1.00
     effic
    0.96
    ſelf
    0.96
     uſ
    0.95
     againſt
    0.95
     himſelf
    0.95
     myſelf
    0.94
     ―――――
    0.93
    Act Density 0.105%

    No Known Activations