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

    Neuronpedia

    INDEX
    Explanations

    references to "grounds" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sins
    -0.69
    thal
    -0.67
     Sachs
    -0.65
     Abyssal
    -0.64
    apt
    -0.63
     Prediction
    -0.63
     sadd
    -0.62
     barrel
    -0.61
    arus
    -0.61
     reconnect
    -0.59
    POSITIVE LOGITS
    keepers
    1.18
    keeper
    1.15
    grounds
    1.03
     grounds
    0.99
    keeping
    0.95
    ground
    0.95
    hog
    0.84
    fare
    0.82
    suit
    0.82
    GROUND
    0.81
    Act Density 0.011%

    No Known Activations