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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a decision or judgment based on certain criteria

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "based on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.81
    bats
    -0.77
    ura
    -0.74
    Sport
    -0.71
    Lab
    -0.71
    zon
    -0.70
    Forge
    -0.69
    flush
    -0.68
    Bit
    -0.68
    Daddy
    -0.66
    POSITIVE LOGITS
     behalf
    0.99
     principles
    0.98
     assumption
    0.93
     assumptions
    0.88
     hears
    0.87
     principle
    0.85
     observation
    0.84
     sheer
    0.84
     conjecture
    0.82
     observations
    0.80
    Act Density 0.095%

    No Known Activations