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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zew
    -0.16
    ATAR
    -0.16
    ecut
    -0.16
    AGR
    -0.15
    cdf
    -0.15
     Glad
    -0.15
     glad
    -0.15
     Apprec
    -0.14
    LOPT
    -0.14
    welcome
    -0.14
    POSITIVE LOGITS
     extend
    0.31
     extends
    0.29
    extend
    0.27
     extent
    0.25
    extends
    0.23
     want
    0.23
     Extend
    0.23
     extents
    0.22
     extended
    0.21
     express
    0.20
    Act Density 0.039%

    No Known Activations