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

    Neuronpedia

    INDEX
    Explanations

    expressions related to eagerness or willingness to participate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.61
    PreferredItem
    -0.57
     betweenstory
    -0.57
     ErrIntOverflow
    -0.55
    RenderAtEndOf
    -0.51
     daripada
    -0.51
    SourceChecksum
    -0.51
    cheibe
    -0.50
    cheiben
    -0.50
    stateProvider
    -0.50
    POSITIVE LOGITS
     by
    0.69
     pinulongan
    0.65
     ale
    0.62
     tak
    0.59
     to
    0.55
     Muck
    0.54
    alete
    0.54
     By
    0.53
     nic
    0.52
    acto
    0.51
    Act Density 0.032%

    No Known Activations