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

    Neuronpedia

    INDEX
    Explanations

    keywords related to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    the character sequence "âĢ" followed by various contextual words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.64
     wink
    -0.62
     handshake
    -0.62
     cyan
    -0.62
     Tunis
    -0.62
     blender
    -0.60
     muse
    -0.60
     dust
    -0.60
     denim
    -0.59
     confinement
    -0.59
    POSITIVE LOGITS
    £
    1.03
    ı
    1.02
    ¹
    0.98
    º
    0.97
    Ĵ
    0.91
    į
    0.89
    Ĩ
    0.89
    ®
    0.88
    §
    0.88
    ¯
    0.87
    Act Density 0.505%

    No Known Activations