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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote preparation or planning for future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Италијани
    -0.77
     الحره
    -0.72
     ModelExpression
    -0.69
    expandindo
    -0.65
    PerformLayout
    -0.65
    tagHelperRunner
    -0.62
    migrationBuilder
    -0.61
    AutoresizingMask
    -0.60
    matchCondition
    -0.59
    下载附件
    -0.58
    POSITIVE LOGITS
     prelude
    0.64
     transitional
    0.54
     precedes
    0.52
     sementara
    0.50
     Prelude
    0.49
     Übergang
    0.49
     precede
    0.48
     placeholder
    0.47
     interim
    0.46
     stepping
    0.46
    Act Density 0.178%

    No Known Activations