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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns followed by specific nouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns referring to individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aunder
    -0.80
    obin
    -0.78
    Balt
    -0.77
    lehem
    -0.77
    ibaba
    -0.76
    ulhu
    -0.75
    :{
    -0.75
    uminati
    -0.74
    Tang
    -0.74
    yang
    -0.74
    POSITIVE LOGITS
     ancestors
    1.16
     superiors
    1.15
     opponents
    1.11
     chances
    1.09
     own
    1.08
     fingerprints
    1.07
     predecessors
    1.06
     adversaries
    1.03
     parents
    1.02
     detractors
    1.01
    Act Density 0.294%

    No Known Activations