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

    Neuronpedia

    INDEX
    Explanations

    references to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.80
    abase
    -0.70
     Klu
    -0.69
    jri
    -0.69
    igslist
    -0.69
    wagon
    -0.68
    dfx
    -0.66
    semb
    -0.65
     Laksh
    -0.62
    awei
    -0.62
    POSITIVE LOGITS
     refresh
    0.82
     learn
    0.76
     subscribe
    0.76
     customize
    0.75
     receive
    0.74
     keep
    0.72
     save
    0.71
     celebrate
    0.70
     navigate
    0.70
     get
    0.68
    Act Density 0.030%

    No Known Activations