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

    Neuronpedia

    INDEX
    Explanations

    phrases related to motion or action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "go."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     positions
    -0.70
     rusty
    -0.64
     illustrated
    -0.62
     Marriott
    -0.62
     evidenced
    -0.60
     tender
    -0.58
     position
    -0.58
     clad
    -0.57
     detected
    -0.57
     hydraulic
    -0.57
    POSITIVE LOGITS
    go
    4.35
    Go
    1.85
    going
    1.82
    GO
    1.82
    gone
    1.58
    went
    1.46
    got
    1.42
    gi
    1.36
    gom
    1.31
    ga
    1.26
    Act Density 0.013%

    No Known Activations