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

    Neuronpedia

    INDEX
    Explanations

    references to personal or collective pronouns indicating involvement or encouragement in an ongoing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’ve
    -0.20
    ’re
    -0.14
    омен
    -0.14
    ÅĻich
    -0.13
    ve
    -0.13
    #
    -0.13
     /*!<
    -0.13
     Longitude
    -0.13
    ziej
    -0.12
    inand
    -0.12
    POSITIVE LOGITS
    'll
    0.42
    'l
    0.38
     ll
    0.38
    ll
    0.37
     will
    0.35
    ,ll
    0.35
    .ll
    0.33
    ’ll
    0.32
     ill
    0.32
     wil
    0.30
    Act Density 0.155%

    No Known Activations