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

    Neuronpedia

    INDEX
    Explanations

    phrases related to construction or creation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "construct" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vide
    -0.61
     spot
    -0.61
     Kris
    -0.59
     Phil
    -0.59
     senior
    -0.59
     Gomez
    -0.58
     cash
    -0.57
    corn
    -0.57
     starring
    -0.57
    nd
    -0.57
    POSITIVE LOGITS
    Construct
    1.33
    smanship
    1.25
     construct
    1.23
     Construct
    1.18
     constructs
    1.15
    ivist
    1.14
    construct
    1.08
    ions
    1.04
    ively
    1.02
    ors
    0.99
    Act Density 0.007%

    No Known Activations