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

    Neuronpedia

    INDEX
    Explanations

    assertive statements regarding truth and falsehood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ivelany
    -0.64
     propOrder
    -0.62
     betweenstory
    -0.61
    Datuak
    -0.58
    phro
    -0.51
    FunctionFlags
    -0.50
    Portály
    -0.49
    LookAnd
    -0.48
    fjspx
    -0.48
    IntoConstraints
    -0.48
    POSITIVE LOGITS
     Monfieur
    1.00
    enumi
    0.91
     Jefus
    0.81
     houſe
    0.80
     ſeveral
    0.77
     becauſe
    0.76
     Houſe
    0.75
     Theſe
    0.75
    siąż
    0.74
     Beſ
    0.74
    Act Density 1.063%

    No Known Activations