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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms associated with identity and similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    openConnection
    -0.56
     digress
    -0.54
     recul
    -0.53
    SequentialGroup
    -0.49
    ADVERTISEMENT
    -0.48
    सत
    -0.47
    engel
    -0.47
    velte
    -0.47
     détour
    -0.46
    cumulative
    -0.46
    POSITIVE LOGITS
     identical
    1.18
     identically
    1.09
    Iden
    1.05
     Iden
    1.04
    identical
    1.03
     similarity
    0.96
    SAME
    0.94
     Similarity
    0.89
     matching
    0.88
    isSame
    0.87
    Act Density 0.728%

    No Known Activations