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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decided."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clad
    -0.78
    aired
    -0.71
    esc
    -0.69
    acking
    -0.68
    capacity
    -0.66
    rake
    -0.65
    outh
    -0.64
    icone
    -0.64
    abytes
    -0.64
    anky
    -0.64
    POSITIVE LOGITS
     Garc
    0.78
     unanimously
    0.75
     upon
    0.74
    ters
    0.70
     differently
    0.66
     calculus
    0.65
     abruptly
    0.63
     decided
    0.63
     decides
    0.63
    RM
    0.62
    Act Density 0.040%

    No Known Activations