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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns followed by a noun or noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and relate them to families or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.78
    imal
    -0.78
    LIN
    -0.76
    LOCK
    -0.76
    Brow
    -0.73
    VER
    -0.73
    ****
    -0.72
    Serv
    -0.72
    Enable
    -0.72
    JECT
    -0.71
    POSITIVE LOGITS
     allies
    1.23
     attendant
    1.19
     successors
    1.11
     surroundings
    1.10
     affiliates
    1.05
     own
    1.04
     predecessors
    1.03
     il
    1.02
     associates
    1.01
     associated
    1.01
    Act Density 0.130%

    No Known Activations