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

    Neuronpedia

    INDEX
    Explanations

    mentions of prices or values increasing

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate an increase or rise in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gemony
    -0.78
    Synopsis
    -0.73
     Aliens
    -0.69
    Parents
    -0.68
    ships
    -0.67
    Closure
    -0.67
    Method
    -0.66
    >[
    -0.63
    Types
    -0.63
    Maker
    -0.62
    POSITIVE LOGITS
    graded
    0.87
    grading
    0.84
    river
    0.84
    stage
    0.81
    cycle
    0.79
    gradation
    0.78
    stairs
    0.78
     stairs
    0.76
    acebook
    0.75
    imate
    0.75
    Act Density 0.020%

    No Known Activations