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

    Neuronpedia

    INDEX
    Explanations

    occurrences of personal pronouns and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onn
    -0.17
    ford
    -0.15
    kke
    -0.15
    Indented
    -0.15
    pong
    -0.15
     flag
    -0.15
    _Flag
    -0.15
    onen
    -0.14
    upil
    -0.14
     Shepherd
    -0.14
    POSITIVE LOGITS
    ins
    0.19
    INS
    0.17
    ies
    0.17
    IES
    0.17
     inspector
    0.16
     IE
    0.16
    .accessToken
    0.15
    hub
    0.15
     prot
    0.15
    proto
    0.15
    Act Density 0.025%

    No Known Activations