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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "subject" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.63
    ombic
    -0.60
    ReusableCell
    -0.57
    ForRow
    -0.57
     newArray
    -0.55
     GenerationType
    -0.55
    $_['
    -0.55
    writerow
    -0.53
    ValueGenerated
    -0.53
    SequentialGroup
    -0.51
    POSITIVE LOGITS
     subject
    5.50
    subject
    4.92
     Subject
    4.80
    Subject
    4.49
     SUBJECT
    4.28
     subjects
    3.98
    SUBJECT
    3.81
     Subjects
    3.55
    subjects
    3.32
    Subjects
    3.10
    Act Density 0.073%

    No Known Activations