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

    Neuronpedia

    INDEX
    Explanations

    terms related to responsibilities and accountability

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

    after "respon" like "sibility", "sive"

    np_acts-logits-general · gemini-2.0-flash

    responsibility and responsiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.52
     default
    -0.49
     словарь
    -0.48
    SequentialGroup
    -0.47
    IRQn
    -0.46
     aj
    -0.43
    letar
    -0.42
    เลย
    -0.42
     רבים
    -0.41
    ayi
    -0.41
    POSITIVE LOGITS
    ability
    0.83
    ness
    0.73
    sibility
    0.72
    HasColumnType
    0.72
    nerable
    0.71
     solubility
    0.71
     tights
    0.68
    vaila
    0.67
    ABILITY
    0.65
    abilidade
    0.64
    Act Density 0.182%

    No Known Activations