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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of crossing or cross-like structures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Cross" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CES
    -0.71
    ERSON
    -0.66
     Rao
    -0.64
     UCH
    -0.63
     Gross
    -0.63
    ufact
    -0.62
    aneously
    -0.60
     vapor
    -0.60
     Pik
    -0.60
    ICAN
    -0.59
    POSITIVE LOGITS
    roads
    1.63
    bow
    1.47
    bones
    1.36
    bows
    1.26
    hair
    1.22
    word
    1.14
    words
    1.06
    rail
    1.04
    walk
    1.02
    es
    1.01
    Act Density 0.029%

    No Known Activations