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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or statements emphasizing similarity or sameness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.19
    rious
    -0.16
     Own
    -0.15
    land
    -0.15
    ses
    -0.15
    iesta
    -0.15
    lio
    -0.15
     Certain
    -0.15
    ng
    -0.14
    ric
    -0.14
    POSITIVE LOGITS
    -sex
    0.43
     thing
    0.40
     exact
    0.28
     kind
    0.27
     amount
    0.26
     sort
    0.25
    -old
    0.24
     basic
    0.24
    -sized
    0.23
     kinds
    0.23
    Act Density 0.066%

    No Known Activations