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

    Neuronpedia

    INDEX
    Explanations

    structured data types, specifically strings and fields associated with them

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

    string field property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.58
    orsese
    -0.49
     joint
    -0.48
    !*\
    -0.48
     Joint
    -0.44
    joint
    -0.43
    buster
    -0.43
    cpt
    -0.42
    +#+#
    -0.42
    SAC
    -0.42
    POSITIVE LOGITS
    putString
    0.60
    IsString
    0.59
     StringField
    0.57
    StringField
    0.57
    StringValue
    0.56
    writeString
    0.56
     strings
    0.55
    StringProperty
    0.54
     StringVar
    0.53
    StringVar
    0.51
    Act Density 0.082%

    No Known Activations