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

    Neuronpedia

    INDEX
    Explanations

    events related to political comeback victories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    losses or failures

    np_acts-logits-general · gemini-2.0-flash

    records of failure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onItemClick
    -0.63
     triom
    -0.59
     successes
    -0.59
    SUCCESS
    -0.58
     triumphs
    -0.58
     triumph
    -0.57
    Успе
    -0.57
    success
    -0.57
     success
    -0.57
     triumphant
    -0.56
    POSITIVE LOGITS
     dismal
    1.14
     worse
    1.09
     losses
    1.08
     worst
    1.07
     loss
    1.06
     disappointing
    1.05
     disastrous
    1.03
    worst
    0.99
    Worse
    0.99
    worse
    0.98
    Act Density 0.462%

    No Known Activations