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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opposition or resistance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to resistance or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.89
    FORE
    -0.81
    foundland
    -0.71
     Stab
    -0.70
     Bones
    -0.69
    SEA
    -0.69
    terday
    -0.67
    ea
    -0.67
     Birds
    -0.65
     Bought
    -0.64
    POSITIVE LOGITS
     buttons
    0.80
     brakes
    0.76
     shoulder
    0.75
     harder
    0.74
     envelope
    0.73
     tighter
    0.73
     levers
    0.71
     boundaries
    0.71
     wedge
    0.71
     shoulders
    0.69
    Act Density 0.188%

    No Known Activations