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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and phrases indicating ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    кÑĥл
    -0.15
     fort
    -0.15
     Fort
    -0.15
    ilst
    -0.15
    zek
    -0.14
    ields
    -0.14
    uteur
    -0.14
     PANEL
    -0.14
    .setup
    -0.14
    auty
    -0.14
    POSITIVE LOGITS
    /current
    0.15
    919
    0.15
    lez
    0.15
    onta
    0.14
    linger
    0.14
    /packages
    0.14
    é¡ĺ
    0.13
     current
    0.13
    current
    0.13
     Ramp
    0.13
    Act Density 0.010%

    No Known Activations