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

    Neuronpedia

    INDEX
    Explanations

    references to political entities and the opinions surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     probably
    -0.91
    probably
    -0.91
    Probably
    -0.85
     Probably
    -0.84
     prolly
    -0.81
    may
    -0.80
     sicuramente
    -0.75
     may
    -0.71
     sicherlich
    -0.70
     doubtless
    -0.69
    POSITIVE LOGITS
     fails
    0.87
     decides
    0.81
     were
    0.81
     fizer
    0.78
     decide
    0.76
     вдруг
    0.73
     yoksa
    0.72
     tiver
    0.72
     ever
    0.71
     forem
    0.70
    Act Density 0.566%

    No Known Activations