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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize certainty or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _WP
    -0.13
    -await
    -0.13
    isors
    -0.13
     dint
    -0.12
    anything
    -0.12
    965
    -0.12
    ieres
    -0.12
    ovu
    -0.12
     Anything
    -0.12
    agua
    -0.12
    POSITIVE LOGITS
     many
    0.27
     certain
    0.26
     times
    0.25
     few
    0.24
     several
    0.23
    nt
    0.22
     no
    0.21
     two
    0.21
    many
    0.20
     still
    0.20
    Act Density 0.071%

    No Known Activations