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

    Neuronpedia

    INDEX
    Explanations

    questions about the location or existence of something

    oai_token-act-pair · gpt-3.5-turbo

    questions and phrases that express inquiry or seek information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iator
    -0.75
    zai
    -0.73
    iors
    -0.72
    cture
    -0.67
    ]=
    -0.67
    prov
    -0.65
    advertisement
    -0.64
    arios
    -0.63
    degree
    -0.62
    erion
    -0.62
    POSITIVE LOGITS
     Wald
    0.73
     nearest
    0.73
     funds
    0.68
     allegiance
    0.68
     inspiration
    0.65
     money
    0.64
    abouts
    0.63
    ?????
    0.60
     fault
    0.59
     loyalty
    0.59
    Act Density 0.102%

    No Known Activations