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

    Neuronpedia

    INDEX
    Explanations

    references to the entity "self", indicating a focus on self-identity or self-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.83
    Хьажоргаш
    -0.60
    DockStyle
    -0.57
    RegistryLite
    -0.55
    bigliamento
    -0.51
    Personendaten
    -0.50
    baguna
    -0.50
     caccia
    -0.50
    Portale
    -0.49
     ufficiali
    -0.49
    POSITIVE LOGITS
     explanatory
    0.59
    destruct
    0.58
     setInterval
    0.57
     sufficiency
    0.50
    存于互联网档案馆
    0.50
    typal
    0.48
    tawesome
    0.47
    OrBuilder
    0.47
    contentView
    0.47
     كومونز
    0.47
    Act Density 0.078%

    No Known Activations