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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used to denote pauses or separations in sentences

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

    connecting clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.50
    wiesen
    -0.45
     Wrestling
    -0.44
    findpost
    -0.43
    Sham
    -0.43
     Inſ
    -0.42
     APE
    -0.42
     comprom
    -0.42
    Chess
    -0.42
    Ero
    -0.42
    POSITIVE LOGITS
     lecz
    0.57
     mijne
    0.53
     žád
    0.49
     Geduld
    0.49
     voegen
    0.49
    puesto
    0.48
     betekenis
    0.48
    zelfde
    0.48
     poiché
    0.47
     geluk
    0.47
    Act Density 0.080%

    No Known Activations