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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to academia and academic performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flake
    -0.18
     Academ
    -0.18
     acad
    -0.17
     Acad
    -0.17
     academy
    -0.17
     academia
    -0.17
    appy
    -0.16
     Academy
    -0.16
    аÑĢÑħ
    -0.16
    족
    -0.15
    POSITIVE LOGITS
    ian
    0.34
    ALLY
    0.21
     freedom
    0.20
     dishonest
    0.20
     rigor
    0.19
    /Instruction
    0.19
    IAN
    0.18
     Freedom
    0.17
     Rig
    0.17
    -commercial
    0.16
    Act Density 0.009%

    No Known Activations