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

    Neuronpedia

    INDEX
    Explanations

    phrases related to return policies and conditions for returning items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fet
    -0.16
    олеÑĤ
    -0.16
    pio
    -0.15
    .googleapis
    -0.15
    /GPL
    -0.15
     UIResponder
    -0.14
    zeÅĦ
    -0.14
    大åĪ©
    -0.14
    /loader
    -0.14
     deck
    -0.14
    POSITIVE LOGITS
     returns
    0.33
     Returns
    0.32
     RETURNS
    0.28
     return
    0.28
     returned
    0.28
    Returns
    0.27
     exchanges
    0.27
     Return
    0.25
    returns
    0.25
    _returns
    0.24
    Act Density 0.042%

    No Known Activations