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

    Neuronpedia

    INDEX
    Explanations

    words related to past or completed actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    adjectives ending in -ed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Хьажоргаш
    -0.53
     dAtA
    -0.51
    unknownFields
    -0.50
     unknownFields
    -0.50
    UniformLocation
    -0.50
    majánló
    -0.48
    Appellants
    -0.47
    standers
    -0.47
     contextLoads
    -0.47
     invokingState
    -0.46
    POSITIVE LOGITS
    Armed
    0.54
     patterned
    0.53
     armed
    0.51
     Armed
    0.51
     padded
    0.49
     flavored
    0.48
     flavoured
    0.47
    lined
    0.46
     masked
    0.46
    WithData
    0.46
    Act Density 0.130%

    No Known Activations