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

    Neuronpedia

    INDEX
    Explanations

    expressions related to time and reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üss
    -0.15
     moon
    -0.14
    sie
    -0.14
     Period
    -0.14
     periods
    -0.14
    984
    -0.14
     gente
    -0.14
     ü
    -0.14
     Vive
    -0.13
     tit
    -0.13
    POSITIVE LOGITS
     fly
    0.35
     flew
    0.33
     flown
    0.30
    -fly
    0.30
     flies
    0.29
    fly
    0.29
     Fly
    0.29
    Fly
    0.29
     flying
    0.27
     Flynn
    0.26
    Act Density 0.063%

    No Known Activations