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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional states and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.81
    SourceChecksum
    -0.81
     ModelExpression
    -0.79
     >=",
    -0.76
    parsedMessage
    -0.72
     parseFrom
    -0.71
     autorytatywna
    -0.69
     étoit
    -0.68
    MessageTagHelper
    -0.68
     avoient
    -0.67
    POSITIVE LOGITS
     indeed
    0.62
    indeed
    0.61
    XmlAccessorType
    0.56
     certainly
    0.54
     terhadap
    0.49
    certainly
    0.47
     että
    0.47
     whether
    0.46
    Indeed
    0.45
    たとえば
    0.45
    Act Density 0.552%

    No Known Activations