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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or people in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flat
    -0.57
     cu
    -0.53
     di
    -0.53
     st
    -0.52
     pr
    -0.51
     collection
    -0.50
     sp
    -0.50
     het
    -0.50
     fixed
    -0.49
     trade
    -0.49
    POSITIVE LOGITS
    someone
    2.34
     anyone
    2.30
     someone
    2.28
    anyone
    2.28
     alguien
    2.19
    Someone
    2.17
    Anyone
    2.03
     anybody
    2.03
     Someone
    2.03
     Anyone
    1.99
    Act Density 0.290%

    No Known Activations