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

    Neuronpedia

    INDEX
    Explanations

    questions in the form of "Is there..." or similar interrogative constructs

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "Is there" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CJ
    -0.68
    ston
    -0.64
    fuck
    -0.62
     cups
    -0.60
     bites
    -0.58
     caffe
    -0.56
     apex
    -0.56
     sucks
    -0.56
    Fight
    -0.55
     coffin
    -0.55
    POSITIVE LOGITS
    abouts
    1.18
    upon
    0.90
    FORE
    0.89
     guiActiveUn
    0.78
    fore
    0.76
    Native
    0.75
    oplan
    0.74
    agame
    0.72
    odynamics
    0.68
    uggest
    0.67
    Act Density 0.034%

    No Known Activations