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

    Neuronpedia

    INDEX
    Explanations

    expressions starting with the phrase "What a" followed by an adjective or descriptor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arent
    -0.82
    gans
    -0.81
    interstitial
    -0.81
    yip
    -0.80
    aimon
    -0.78
    Topics
    -0.78
    aspers
    -0.77
    icans
    -0.76
    rences
    -0.76
    ◼
    -0.75
    POSITIVE LOGITS
     wrench
    0.85
     nause
    0.80
     shame
    0.79
     miserable
    0.75
     difference
    0.75
     sad
    0.74
     unemploy
    0.74
     evening
    0.73
     disgusting
    0.73
     flawed
    0.72
    Act Density 0.028%

    No Known Activations