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

    Neuronpedia

    INDEX
    Explanations

    adjectives conveying a large amount of intensity or magnitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of significant impact or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    crow
    -0.88
    arers
    -0.87
    tag
    -0.81
    okes
    -0.80
    cling
    -0.77
    cker
    -0.76
    illet
    -0.76
    door
    -0.75
    olog
    -0.75
    pper
    -0.74
    POSITIVE LOGITS
     amounts
    1.08
     amount
    1.02
     quantities
    0.94
     earthqu
    0.88
     strides
    0.87
     importance
    0.86
     volumes
    0.84
     leaps
    0.84
     lengths
    0.83
     hardship
    0.82
    Act Density 0.044%

    No Known Activations