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

    Neuronpedia

    INDEX
    Explanations

    references to fans and followers in varied contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to sports fans and their emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kills
    -0.73
    hua
    -0.66
    KO
    -0.60
    expensive
    -0.59
     Theft
    -0.58
    Favorite
    -0.57
     Killed
    -0.56
     Defeat
    -0.56
     Mechanical
    -0.55
    Virgin
    -0.55
    POSITIVE LOGITS
     finally
    1.16
     anew
    1.01
     suddenly
    1.00
     wondered
    1.00
     poised
    0.96
     understandably
    0.93
     resumed
    0.90
     beck
    0.87
     urgently
    0.87
     wondering
    0.86
    Act Density 0.513%

    No Known Activations