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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their context in sentences

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

    officials and spokespeople

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Whilst
    -0.65
     Infatti
    -0.62
     therefore
    -0.60
     Whilst
    -0.60
     bahkan
    -0.59
     addirittura
    -0.59
    Therefore
    -0.59
     inilah
    -0.57
     Therefore
    -0.57
     przecież
    -0.56
    POSITIVE LOGITS
    BeginContext
    0.60
     queſta
    0.57
     officials
    0.55
     spokesman
    0.55
     XNUMX
    0.54
     inci
    0.50
     aides
    0.50
     Reuters
    0.50
     profan
    0.49
     sere
    0.49
    Act Density 0.022%

    No Known Activations