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

    Neuronpedia

    INDEX
    Explanations

    expressions of relationships and social dynamics

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

    Auxiliary verbs (can, will, could, might, have)

    np_acts-logits-general · gemini-2.0-flash

    modal verb followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.78
     Jefus
    -0.76
     quæ
    -0.71
     houſe
    -0.69
     Majefty
    -0.67
    blockList
    -0.67
    ✨:
    -0.67
     ostavi
    -0.66
     Савезне
    -0.66
    WithIOException
    -0.65
    POSITIVE LOGITS
    まで
    0.51
                              
    0.45
    дже
    0.45
    puis
    0.44
    urn
    0.44
     तब
    0.43
     potentially
    0.42
     este
    0.41
     actually
    0.41
    Actually
    0.41
    Act Density 0.152%

    No Known Activations