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

    Neuronpedia

    INDEX
    Explanations

    contractions and forms of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wik
    -0.15
    agog
    -0.15
    ansi
    -0.15
    oui
    -0.15
    ÑĢеж
    -0.14
    alo
    -0.14
     itself
    -0.14
    że
    -0.14
    abra
    -0.14
    ori
    -0.14
    POSITIVE LOGITS
     welcome
    0.24
    Welcome
    0.21
    welcome
    0.21
     Welcome
    0.21
     hereby
    0.19
     lucky
    0.19
     forgiven
    0.17
     fortunate
    0.17
     wasting
    0.17
    ylland
    0.17
    Act Density 0.089%

    No Known Activations