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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions, particularly "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jspb
    -0.54
     protoimpl
    -0.52
    المناصب
    -0.51
    UnknownFieldSet
    -0.50
     betweenstory
    -0.49
    CloseOperation
    -0.48
    oredCriteria
    -0.48
    msgTypes
    -0.43
    WindowConstants
    -0.43
    IContainer
    -0.41
    POSITIVE LOGITS
     yet
    0.96
     yes
    0.92
     they
    0.82
     rightly
    0.82
     indeed
    0.79
     it
    0.78
     frankly
    0.77
     conversely
    0.76
     importantly
    0.75
     we
    0.75
    Act Density 0.551%

    No Known Activations