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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical groups, particularly those starting with the letter "G" and a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the placeholder token "<|endoftext|>"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remotely
    -0.66
     retrospect
    -0.65
    puter
    -0.64
     sight
    -0.64
     craw
    -0.63
     refere
    -0.61
     divest
    -0.61
     lawn
    -0.61
     Grizz
    -0.61
     cle
    -0.60
    POSITIVE LOGITS
    oliath
    1.33
    CHQ
    1.21
    ossip
    1.21
    reetings
    1.20
    opher
    1.20
    irlfriend
    1.18
    ourmet
    1.17
    EO
    1.17
    ospels
    1.16
    ilded
    1.13
    Act Density 0.044%

    No Known Activations