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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive emotions related to announcements or collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.88
    RegressionTest
    -0.86
     transfieras
    -0.78
    nasse
    -0.74
     Maradona
    -0.74
    ThroughAttribute
    -0.74
    исленность
    -0.73
    XmlAccessType
    -0.71
    Puck
    -0.70
     fays
    -0.70
    POSITIVE LOGITS
     Gros
    0.57
     welcome
    0.56
     larmes
    0.55
     delight
    0.54
     bienvenida
    0.52
    gjenge
    0.52
     Compet
    0.52
     getRole
    0.52
     entour
    0.51
    gaven
    0.51
    Act Density 0.065%

    No Known Activations