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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "earlier" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chal
    -0.16
    úc
    -0.15
     little
    -0.15
    yla
    -0.15
    DES
    -0.14
     older
    -0.14
    im
    -0.14
    oons
    -0.14
    icum
    -0.14
     ancient
    -0.14
    POSITIVE LOGITS
    -than
    0.33
    _than
    0.31
     than
    0.29
     THAN
    0.26
    than
    0.24
    Than
    0.23
     Than
    0.21
     вÑģего
    0.20
     než
    0.20
    _THAN
    0.20
    Act Density 0.014%

    No Known Activations