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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and pronouns that indicate entities, relationships, or subjects in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    леÑĩ
    -0.18
     GOODMAN
    -0.15
    ouser
    -0.14
    ľ
    -0.14
    EMENT
    -0.14
    unch
    -0.14
    ANEL
    -0.14
    IBUT
    -0.14
    LING
    -0.14
    iring
    -0.13
    POSITIVE LOGITS
    ouv
    0.17
    ittest
    0.17
    _registro
    0.17
    /content
    0.16
    ovol
    0.15
    unner
    0.15
    gart
    0.15
     repr
    0.14
     Tal
    0.14
    bridge
    0.14
    Act Density 0.007%

    No Known Activations