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

    Neuronpedia

    INDEX
    Explanations

    connections between individuals and mentorship roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Adjacent
    -0.14
     Straw
    -0.14
    oust
    -0.14
    สว
    -0.14
    iller
    -0.14
    orm
    -0.13
     ActionTypes
    -0.13
    ĨĴ
    -0.13
    stud
    -0.13
    calar
    -0.13
    POSITIVE LOGITS
     mentor
    0.45
     mentors
    0.39
    mentor
    0.36
     mentoring
    0.35
     Mentor
    0.35
     Ment
    0.30
     ment
    0.29
     coach
    0.28
     guidance
    0.27
     guide
    0.24
    Act Density 0.236%

    No Known Activations