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

    Neuronpedia

    INDEX
    Explanations

    cases of offers being made or accepted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "offer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cling
    -0.71
    DW
    -0.68
     destruct
    -0.65
    icent
    -0.62
     Cav
    -0.59
     Cabin
    -0.59
     pride
    -0.56
     Maintenance
    -0.56
    error
    -0.56
    ansk
    -0.56
    POSITIVE LOGITS
    igslist
    0.84
    ļéĨĴ
    0.83
    xual
    0.78
    backs
    0.76
    holder
    0.74
     offered
    0.73
     bribes
    0.73
    ointment
    0.72
    pta
    0.71
    vier
    0.70
    Act Density 0.031%

    No Known Activations