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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning progress and moving ahead

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azo
    -0.71
    insk
    -0.70
    rip
    -0.65
    lez
    -0.64
    chens
    -0.63
    xs
    -0.62
    anguage
    -0.60
    LES
    -0.59
    colo
    -0.59
    ENA
    -0.58
    POSITIVE LOGITS
    olicy
    0.89
     puberty
    0.82
    wards
    0.80
    stairs
    0.77
    WARD
    0.75
    stage
    0.75
    uberty
    0.72
    gradation
    0.68
    comings
    0.67
    roth
    0.67
    Act Density 0.016%

    No Known Activations