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

    Neuronpedia

    INDEX
    Explanations

    repeated names or titles of characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dépens
    -0.68
    MERGE
    -0.57
     metropolitana
    -0.56
     للمعارف
    -0.56
    Merged
    -0.56
     détach
    -0.54
    verge
    -0.53
     Grains
    -0.53
     rendus
    -0.51
     précédents
    -0.50
    POSITIVE LOGITS
     Sammy
    0.78
    Sammy
    0.74
     Johnny
    0.70
     Jimmy
    0.70
     johnny
    0.69
     Bobby
    0.69
     Ronnie
    0.68
     buddy
    0.68
     Freddie
    0.67
    Bobby
    0.67
    Act Density 0.276%

    No Known Activations