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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief or personal conviction

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

    I believe construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     désert
    -0.46
     procès
    -0.46
     portail
    -0.44
     pourtant
    -0.44
     chantier
    -0.43
     sorpresas
    -0.43
     démocr
    -0.42
     Cómo
    -0.42
     lendemain
    -0.41
     pauvres
    -0.39
    POSITIVE LOGITS
     believe
    0.68
     Audiodateien
    0.66
     GenerationType
    0.62
     transfieras
    0.59
    withIdentifier
    0.57
    saraba
    0.56
    believe
    0.55
    eavour
    0.54
    fjspx
    0.53
    rungsseite
    0.52
    Act Density 0.014%

    No Known Activations