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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to algorithms and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.77
     становника
    -0.55
    Джерела
    -0.52
     CreateTagHelper
    -0.51
    chè
    -0.51
    ViewFeatures
    -0.51
    DebuggerStep
    -0.49
    Hozzáférés
    -0.48
    ⓧ
    -0.48
    efeller
    -0.48
    POSITIVE LOGITS
    +#+#
    0.71
     adap
    0.66
     train
    0.63
     greed
    0.62
     learn
    0.60
     trains
    0.59
    apunov
    0.58
    trains
    0.56
     learns
    0.56
     estimés
    0.56
    Act Density 0.878%

    No Known Activations