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

    Neuronpedia

    INDEX
    Explanations

    references to food preservation and mechanical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sneered
    -0.67
     wept
    -0.57
     chuckled
    -0.55
     scoffed
    -0.54
     sneer
    -0.53
     growled
    -0.53
     hers
    -0.53
    ('/:
    -0.52
     demur
    -0.51
     Lieberman
    -0.51
    POSITIVE LOGITS
     itſelf
    0.88
     whoſe
    0.81
     myſelf
    0.79
    ſelves
    0.79
    ^(@)
    0.75
    ſelf
    0.74
     purpoſe
    0.74
     pleaſure
    0.71
     themſelves
    0.71
     ―――――
    0.71
    Act Density 0.998%

    No Known Activations