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

    Neuronpedia

    INDEX
    Explanations

    words that denote active participation or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.86
    Wann
    -0.84
    ✨:
    -0.82
     betweenstory
    -0.78
     =&
    -0.76
     Mapp
    -0.72
    Gli
    -0.72
    lujah
    -0.72
    roleum
    -0.71
    MigrationBuilder
    -0.71
    POSITIVE LOGITS
     active
    2.80
     Active
    2.67
    Active
    2.60
    active
    2.52
     ACTIVE
    2.47
    ACTIVE
    2.19
     actives
    2.07
     activo
    1.94
     aktive
    1.88
     attivo
    1.86
    Act Density 0.069%

    No Known Activations