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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases initiating with "That."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.57
    oa̍t
    -0.50
    adaptiveStyles
    -0.48
    DockStyle
    -0.46
    tagHelperRunner
    -0.45
    HasIndex
    -0.45
     transférez
    -0.44
    lighting
    -0.43
     Infórmanos
    -0.43
     queſta
    -0.42
    POSITIVE LOGITS
     begs
    0.57
     aside
    0.57
     means
    0.56
     explains
    0.56
     sounds
    0.47
     concludes
    0.47
     leads
    0.46
     alone
    0.46
     brings
    0.46
     said
    0.43
    Act Density 0.294%

    No Known Activations