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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases indicating various levels of achievement or performance

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and phrases that express the quality of performance or achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hops
    -0.88
    aucuses
    -0.78
    ULTS
    -0.76
    ingers
    -0.72
    andals
    -0.71
    ources
    -0.71
    uits
    -0.71
     Units
    -0.70
    classes
    -0.69
    iddles
    -0.69
    POSITIVE LOGITS
     amount
    0.95
     impression
    0.90
     dose
    0.89
     foothold
    0.87
     comeback
    0.87
     berth
    0.85
     glance
    0.83
     chunk
    0.81
     burden
    0.79
     bead
    0.78
    Act Density 0.248%

    No Known Activations