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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seven
    -0.16
     addCriterion
    -0.16
     Seven
    -0.15
    aby
    -0.15
     six
    -0.15
     ä¸ĥ
    -0.15
     seven
    -0.15
    vier
    -0.15
     åħŃ
    -0.14
    .Ribbon
    -0.14
    POSITIVE LOGITS
    9
    0.48
    914
    0.34
    915
    0.32
    919
    0.32
    913
    0.31
    912
    0.31
    920
    0.31
    09
    0.31
    916
    0.30
    91
    0.30
    Act Density 0.068%

    No Known Activations