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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.16
    #error
    -0.16
    ä¸įåĪ°
    -0.15
    685
    -0.15
    .fhir
    -0.15
    667
    -0.14
    tal
    -0.14
     Majority
    -0.14
    æŀĿ
    -0.14
    710
    -0.13
    POSITIVE LOGITS
     advance
    0.45
    advance
    0.38
     Advance
    0.36
    Advance
    0.34
    .advance
    0.30
     advances
    0.27
     ahead
    0.26
    _advance
    0.24
    ahead
    0.24
    Ahead
    0.23
    Act Density 0.020%

    No Known Activations