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

    Neuronpedia

    INDEX
    Explanations

    evaluative statements about people or situations

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

    "to be"

    np_acts-logits-general · gemini-2.0-flash

    seems to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     respectivement
    -0.48
     reportedly
    -0.47
     probablemente
    -0.45
     allegedly
    -0.44
     seguramente
    -0.43
     blandt
    -0.42
     sicuramente
    -0.41
     ferdig
    -0.41
     undoubtedly
    -0.41
     tentunya
    -0.40
    POSITIVE LOGITS
    EDEFAULT
    0.99
    DockStyle
    0.98
    WithIOException
    0.95
     EconPapers
    0.93
     >=",
    0.93
    ineno
    0.92
     ***!
    0.90
    enumi
    0.90
     виправивши
    0.89
    ReusableCell
    0.88
    Act Density 0.160%

    No Known Activations