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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reference or alluding to specific people or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "referring" and its variations, indicating discussions about citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ija
    -0.58
    lite
    -0.56
    bred
    -0.55
     foothold
    -0.52
    morrow
    -0.52
    houses
    -0.51
    stars
    -0.51
    hov
    -0.51
    driving
    -0.51
    lishes
    -0.51
    POSITIVE LOGITS
     to
    1.10
     thereto
    0.97
     specifically
    0.91
     sarcast
    0.78
     directly
    0.76
    to
    0.73
    Pause
    0.68
    To
    0.68
     favorably
    0.68
     derog
    0.66
    Act Density 0.054%

    No Known Activations