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

    Neuronpedia

    INDEX
    Explanations

    expressions of irony and surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOPQRST
    -0.53
     meriva
    -0.52
     scania
    -0.52
    сюда
    -0.51
     Merlin
    -0.51
     Manus
    -0.50
     aerop
    -0.48
     hydra
    -0.48
     behövs
    -0.48
    zegorz
    -0.47
    POSITIVE LOGITS
    Surprisingly
    0.71
    竟
    0.70
     surprisingly
    0.70
    xically
    0.69
     ironically
    0.68
    居然
    0.67
     Ironically
    0.67
     estimés
    0.66
    prisingly
    0.63
    竟然
    0.62
    Act Density 0.260%

    No Known Activations