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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a large quantity or multiple options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     most
    -0.16
    opic
    -0.14
     anything
    -0.14
     eines
    -0.13
    358
    -0.13
    ãĤĪãģı
    -0.13
    odings
    -0.13
    izz
    -0.13
    æľĢ
    -0.13
    ambda
    -0.13
    POSITIVE LOGITS
     ways
    0.42
     reasons
    0.33
     Ways
    0.31
     reason
    0.27
    reason
    0.26
     places
    0.25
    ways
    0.24
     Reasons
    0.24
    Reason
    0.23
     occasions
    0.21
    Act Density 0.112%

    No Known Activations