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

    Neuronpedia

    INDEX
    Explanations

    the term "interesting" and variations of it, indicating a focus on novelty or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cidas
    -0.52
     démarche
    -0.51
    kson
    -0.51
     poignée
    -0.49
    erde
    -0.49
     slog
    -0.48
     Ansprüche
    -0.48
    ague
    -0.45
    odal
    -0.45
     lashes
    -0.45
    POSITIVE LOGITS
     interesting
    2.02
    interesting
    1.93
     Interesting
    1.79
    Interesting
    1.67
     fascinating
    1.41
    +#+#
    1.33
     interessante
    1.30
     intéressante
    1.22
     interesante
    1.21
     intéressant
    1.21
    Act Density 0.067%

    No Known Activations