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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrasting information

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases that introduce contrasts or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enced
    -0.79
     Yuan
    -0.60
     encyclopedia
    -0.55
    vernment
    -0.54
     regress
    -0.52
    olescent
    -0.51
    mod
    -0.51
     pedal
    -0.51
    authorized
    -0.51
     Wheel
    -0.50
    POSITIVE LOGITS
    soever
    0.72
     guiActiveUn
    0.71
     ie
    0.70
    ussen
    0.70
    ickets
    0.68
     Whilst
    0.68
     Cricket
    0.67
     dont
    0.66
    ,,,,
    0.65
    FW
    0.64
    Act Density 0.367%

    No Known Activations