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

    Neuronpedia

    INDEX
    Explanations

    sequences and patterns in numerical or symbolic data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >-
    -0.49
    }}-\
    -0.42
    ztes
    -0.42
    dicos
    -0.42
    ức
    -0.41
    phat
    -0.40
     Ghan
    -0.40
    }-\
    -0.40
     &_
    -0.40
    hede
    -0.40
    POSITIVE LOGITS
    [
    1.51
     [
    1.48
    findpost
    1.23
     $[
    1.18
    ()[
    1.02
    }[
    1.00
    '][
    0.99
    {[
    0.98
    　　[
    0.98
    .[
    0.97
    Act Density 0.528%

    No Known Activations