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

    Neuronpedia

    INDEX
    Explanations

    content related to requests and directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.65
    findpost
    -0.52
     Réponses
    -0.49
     simplifié
    -0.47
     betweenstory
    -0.47
     виправивши
    -0.46
    principalTable
    -0.46
    ThemeOverlay
    -0.45
    modelBuilder
    -0.44
     AspNetCore
    -0.44
    POSITIVE LOGITS
    는
    0.61
    은
    0.60
     basically
    0.55
     memang
    0.54
     quite
    0.53
    에는
    0.53
     auroit
    0.53
     étant
    0.53
     đã
    0.52
     δεν
    0.51
    Act Density 0.027%

    No Known Activations