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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate relationships and dependencies in contexts like development or health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.68
     ✭✭
    -0.61
    ImageContext
    -0.57
    AxisAlignment
    -0.56
     onAnimation
    -0.56
     Meld
    -0.54
    WebMethod
    -0.53
    Meld
    -0.52
     AssemblyTitle
    -0.52
    bellum
    -0.52
    POSITIVE LOGITS
     consequently
    1.27
     therefore
    1.09
     correspondingly
    1.02
     donc
    1.01
     Consequently
    0.99
     accordingly
    0.95
    也就
    0.94
     hence
    0.93
    Consequently
    0.92
     соответственно
    0.91
    Act Density 0.621%

    No Known Activations