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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exus
    -0.20
    DDL
    -0.18
    638
    -0.15
    .Generated
    -0.15
    abar
    -0.14
    prech
    -0.14
     Foley
    -0.14
    .scalablytyped
    -0.14
     Fog
    -0.14
     ÏĢεÏģί
    -0.14
    POSITIVE LOGITS
    usi
    0.17
    eli
    0.17
    udu
    0.15
    oir
    0.15
    rong
    0.15
    HL
    0.15
    EATURE
    0.15
    har
    0.14
    ell
    0.14
     try
    0.14
    Act Density 0.080%

    No Known Activations