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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating anticipation or future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.86
    o
    -0.84
    stalline
    -0.74
    ization
    -0.70
    bruno
    -0.70
     Jones
    -0.69
     Bro
    -0.68
     X
    -0.67
      
    -0.66
    Становништво
    -0.64
    POSITIVE LOGITS
     ahead
    1.69
     Ahead
    1.68
     AHEAD
    1.59
    ahead
    1.45
    Ahead
    1.39
     himſelf
    1.18
     myſelf
    1.15
     ſeveral
    1.07
     Majefty
    1.06
     Theſe
    1.01
    Act Density 0.077%

    No Known Activations