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

    Neuronpedia

    INDEX
    Explanations

    phrases related to vehicle steering

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Ste" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nas
    -0.68
     Boo
    -0.66
     numbered
    -0.60
     Curve
    -0.59
     viewing
    -0.58
     contracting
    -0.58
     ana
    -0.57
     liking
    -0.56
    OST
    -0.55
     probable
    -0.54
    POSITIVE LOGITS
    ampunk
    1.42
    pping
    1.24
    ffen
    1.18
    uben
    1.16
    ppe
    1.10
    chnology
    1.09
    pped
    1.09
    alth
    1.07
    uart
    1.04
    ppers
    1.04
    Act Density 0.030%

    No Known Activations