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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference the nature or properties of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.18
    UFFIX
    -0.15
    оиÑĤ
    -0.14
    ãĥ¬ãĥĥãĥĪ
    -0.14
     Sheridan
    -0.14
    SSF
    -0.14
    olf
    -0.14
    Ïģιο
    -0.14
    DITION
    -0.13
    γοÏģ
    -0.13
    POSITIVE LOGITS
     kind
    0.52
     sort
    0.46
    kind
    0.45
     KIND
    0.42
     Kind
    0.40
     species
    0.39
    .kind
    0.39
    種
    0.37
    Kind
    0.37
    sort
    0.37
    Act Density 0.042%

    No Known Activations