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

    Neuronpedia

    INDEX
    Explanations

    phrases related to goals or objectives in a document

    oai_token-act-pair · gpt-3.5-turbo

    phrases and structures that indicate objectives or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isms
    -0.80
    rimp
    -0.71
    dayName
    -0.70
    aults
    -0.70
    rums
    -0.69
    case
    -0.69
    ashtra
    -0.67
    leep
    -0.67
    iaries
    -0.66
    rings
    -0.64
    POSITIVE LOGITS
     this
    0.79
     constructing
    0.77
     these
    0.74
    ENTION
    0.71
     Operation
    0.71
     combating
    0.70
     determining
    0.69
     preserving
    0.69
     establishing
    0.69
     policing
    0.68
    Act Density 0.133%

    No Known Activations