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

    Neuronpedia

    INDEX
    Explanations

    terms associated with agreement or consensus in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukk
    -0.49
    httphttps
    -0.49
    Enlaces
    -0.48
     probe
    -0.47
    longValue
    -0.47
    ientôt
    -0.47
     विश्वसनीयता
    -0.47
    الدراسه
    -0.47
     lenker
    -0.46
    ulka
    -0.46
    POSITIVE LOGITS
    IsContent
    0.91
     consensus
    0.72
    consensus
    0.68
     newState
    0.64
    msgTypes
    0.62
     voldo
    0.61
    TabIndex
    0.60
    Espèce
    0.60
    SourceChecksum
    0.60
    fool
    0.57
    Act Density 2.033%

    No Known Activations