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

    Neuronpedia

    INDEX
    Explanations

    references to interviews and related experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.71
     estekak
    -0.67
     propOrder
    -0.66
     surla
    -0.66
    tagHelperRunner
    -0.65
     defaultstate
    -0.64
    ValueStyle
    -0.61
    httphttps
    -0.59
     ProtoMessage
    -0.59
     utilisateur
    -0.59
    POSITIVE LOGITS
     interview
    0.55
    new
    0.51
     new
    0.45
    awancara
    0.43
     entrevista
    0.42
    max
    0.41
     Interview
    0.40
    sq
    0.39
     töö
    0.37
    stop
    0.35
    Act Density 0.286%

    No Known Activations