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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "back" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BACK
    -0.22
     Back
    -0.22
    back
    -0.22
    Back
    -0.20
     backs
    -0.20
    edback
    -0.20
    backs
    -0.20
     BACK
    -0.19
     backing
    -0.19
    _back
    -0.19
    POSITIVE LOGITS
    wards
    0.24
     wards
    0.20
     whence
    0.19
     home
    0.18
    logged
    0.18
    WARDS
    0.18
    yards
    0.16
    roads
    0.16
    slashes
    0.16
    tracking
    0.16
    Act Density 0.049%

    No Known Activations