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

    Neuronpedia

    INDEX
    Explanations

    phrases related to examining or looking into specific topics or subjects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    TY
    -0.69
    usercontent
    -0.68
    photo
    -0.67
     gasp
    -0.63
    Jar
    -0.63
    borgh
    -0.62
    iere
    -0.62
     Sabha
    -0.61
    isSpecialOrderable
    -0.60
    âĤ¬
    -0.60
    POSITIVE LOGITS
     topics
    1.20
     how
    0.99
     aspects
    0.94
     why
    0.93
     facets
    0.84
     feasibility
    0.83
     trends
    0.81
     issues
    0.80
     whether
    0.78
     matters
    0.78
    Act Density 1.456%

    No Known Activations