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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures, news broadcasting, and commentary

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inates
    -0.91
    relative
    -0.76
    RED
    -0.71
    urally
    -0.67
    metic
    -0.66
    cles
    -0.66
    ifice
    -0.65
    mine
    -0.65
    holes
    -0.64
    ifiable
    -0.64
    POSITIVE LOGITS
    star
    0.95
     Morning
    0.94
     Consult
    0.85
     Madness
    0.82
    night
    0.81
     Glory
    0.77
     Dew
    0.77
    aturdays
    0.77
     Caller
    0.76
     Evening
    0.74
    Act Density 0.023%

    No Known Activations