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

    Neuronpedia

    INDEX
    Explanations

    adjectives that express awe or admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     />\
    -0.78
    hamshire
    -0.74
     Floren
    -0.74
    ymce
    -0.73
    ticelli
    -0.72
    Botswana
    -0.72
     fusca
    -0.71
     Etrus
    -0.69
    WebControls
    -0.69
     Hobbit
    -0.68
    POSITIVE LOGITS
    amazing
    1.28
     amazing
    1.27
    Amazing
    1.24
    AMAZING
    1.23
     Amazing
    1.19
     AMAZING
    1.03
     amaz
    0.80
     amazed
    0.77
     amaze
    0.75
     incrível
    0.75
    Act Density 0.060%

    No Known Activations