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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bound
    -0.71
    animate
    -0.71
    Bound
    -0.65
    tis
    -0.63
     Ascension
    -0.63
    adden
    -0.61
    !/
    -0.60
     approximation
    -0.59
     Binding
    -0.59
    endi
    -0.59
    POSITIVE LOGITS
     cautioned
    1.08
     noted
    1.06
     criticized
    1.05
     thanked
    1.03
     criticised
    1.01
     wondered
    1.01
     highlighted
    1.01
     addressed
    1.00
     emphasized
    0.99
     praised
    0.99
    Act Density 0.063%

    No Known Activations