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

    Neuronpedia

    INDEX
    Explanations

    references to active and passive qualities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     theorist
    -0.51
    racked
    -0.51
     tasche
    -0.49
     Teenage
    -0.49
     taped
    -0.48
     Juris
    -0.48
    acks
    -0.48
     chibi
    -0.48
     abusive
    -0.47
     Testi
    -0.47
    POSITIVE LOGITS
    wake
    0.67
     wake
    0.66
     Engine
    0.63
    Active
    0.58
     active
    0.54
    StoryboardSegue
    0.54
    Wake
    0.54
    Engine
    0.52
     actively
    0.52
     Wake
    0.51
    Act Density 0.172%

    No Known Activations