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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an opinion or assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESE
    -0.83
    iership
    -0.78
    ests
    -0.74
    BAT
    -0.71
    ULTS
    -0.70
    utherland
    -0.69
    eful
    -0.69
    uers
    -0.69
    HAEL
    -0.68
    ACA
    -0.66
    POSITIVE LOGITS
     messed
    0.92
     screwed
    0.91
     sucked
    0.80
     bum
    0.80
     neat
    0.79
     sucks
    0.78
     fucked
    0.77
     reminds
    0.77
     lame
    0.77
     creepy
    0.75
    Act Density 0.058%

    No Known Activations