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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "standing."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ults
    -0.78
    ividual
    -0.73
    catentry
    -0.72
    acters
    -0.71
    ELF
    -0.67
    lege
    -0.66
    ²¾
    -0.65
    lance
    -0.63
     msec
    -0.63
    vous
    -0.63
    POSITIVE LOGITS
     rooft
    1.21
     behalf
    1.21
    shore
    1.05
     top
    1.02
     borrowed
    1.01
     scraps
    0.97
    site
    0.97
     shore
    0.95
     roofs
    0.93
     fumes
    0.93
    Act Density 0.173%

    No Known Activations