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

    Neuronpedia

    INDEX
    Explanations

    phrases related to schedules and participation logistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĬĿ
    -0.16
    brick
    -0.16
     ç¥
    -0.15
    è·ĿéĽ¢
    -0.15
    ibal
    -0.14
    èĽĽ
    -0.14
     brick
    -0.14
    urgeon
    -0.14
     bricks
    -0.13
    LOUR
    -0.13
    POSITIVE LOGITS
     Hed
    0.33
     Intern
    0.33
     intern
    0.29
     hed
    0.29
    Intern
    0.29
     shift
    0.27
     interns
    0.26
     Candidate
    0.25
     shifts
    0.25
     Candidates
    0.25
    Act Density 0.000%

    No Known Activations