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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating a need for improvement or solutions to existing problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.61
    MessageOf
    -0.58
    sizeCache
    -0.57
    Cubit
    -0.50
     importanza
    -0.50
     onCancelled
    -0.50
    centiles
    -0.49
    InitVars
    -0.48
     INSEE
    -0.48
    Insn
    -0.48
    POSITIVE LOGITS
     alternative
    0.76
     propOrder
    0.68
     alternatives
    0.65
     reliable
    0.63
     dependable
    0.60
    adaptiveStyles
    0.59
     tool
    0.57
     Alternative
    0.56
     affordable
    0.56
    DockStyle
    0.56
    Act Density 0.311%

    No Known Activations