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

    Neuronpedia

    INDEX
    Explanations

    mentions of job offers or business transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to job or contract offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cling
    -0.75
    lean
    -0.69
    icent
    -0.65
    error
    -0.64
    DW
    -0.63
    carry
    -0.62
     Adventures
    -0.61
     Maintenance
    -0.61
    sight
    -0.60
    san
    -0.59
    POSITIVE LOGITS
    xual
    0.77
     offered
    0.77
    holder
    0.75
    eters
    0.74
    ļéĨĴ
    0.72
    igslist
    0.69
     bribes
    0.69
    emaker
    0.68
    pta
    0.68
     proposition
    0.68
    Act Density 0.025%

    No Known Activations