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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significance or importance in achieving goals or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating influential or key roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.74
    Compar
    -0.74
    raph
    -0.70
     behaves
    -0.69
    cit
    -0.68
    types
    -0.68
    Ther
    -0.67
    Self
    -0.67
    Temperature
    -0.64
     gri
    -0.63
    POSITIVE LOGITS
     drafting
    0.96
     founding
    0.94
     pioneering
    0.90
     shaping
    0.87
     usher
    0.85
     inspiring
    0.79
     establishing
    0.77
     countless
    0.76
     successful
    0.75
     unsuccessful
    0.75
    Act Density 0.346%

    No Known Activations