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

    Neuronpedia

    INDEX
    Explanations

    phrases and terminology related to support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fleming
    -0.73
    Hg
    -0.72
    ✨:
    -0.71
    JDK
    -0.69
     Jes
    -0.68
     Geh
    -0.67
    omitempty
    -0.66
     Latimer
    -0.66
    ريبة
    -0.66
     Vegas
    -0.65
    POSITIVE LOGITS
     support
    1.72
     supports
    1.61
     Supports
    1.57
     Support
    1.56
    Support
    1.55
    support
    1.48
     SUPPORT
    1.47
    Supports
    1.45
     suppor
    1.43
    supports
    1.42
    Act Density 0.143%

    No Known Activations