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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the concept of being "out of" something or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.70
    ValueStyle
    -0.67
    endphp
    -0.65
    apimachinery
    -0.63
    iecie
    -0.60
     esternos
    -0.59
    шкан
    -0.58
    testify
    -0.58
     AssemblyTitle
    -0.55
    flikt
    -0.54
    POSITIVE LOGITS
     nowhere
    1.00
     bounds
    0.91
     sight
    0.80
     reach
    0.77
     necessity
    0.75
     whack
    0.74
     proportion
    0.73
     town
    0.70
     context
    0.68
     pocket
    0.67
    Act Density 0.082%

    No Known Activations