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

    Neuronpedia

    INDEX
    Explanations

    references to personal struggles and life choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Instruction
    -0.20
     Instruction
    -0.18
     instructional
    -0.18
    kus
    -0.17
    .WinForms
    -0.16
    usk
    -0.15
    lander
    -0.14
    cesso
    -0.14
    inker
    -0.14
    insk
    -0.14
    POSITIVE LOGITS
     studying
    0.36
     uni
    0.34
     study
    0.33
     university
    0.33
     studies
    0.31
     degree
    0.30
     Stud
    0.30
     University
    0.29
    Uni
    0.28
     tertiary
    0.28
    Act Density 0.395%

    No Known Activations