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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attracting attention or investment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oops
    -0.69
     timestamp
    -0.67
    jab
    -0.64
     recount
    -0.62
     Printed
    -0.58
     format
    -0.58
     sleeve
    -0.57
     annex
    -0.57
     Abbey
    -0.57
    arat
    -0.56
    POSITIVE LOGITS
     attention
    1.06
     unwanted
    0.84
    entious
    0.81
     crowds
    0.74
     unwelcome
    0.72
    xual
    0.72
    kefeller
    0.72
     attracted
    0.71
     hordes
    0.71
    dinand
    0.71
    Act Density 0.041%

    No Known Activations