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

    Neuronpedia

    INDEX
    Explanations

    elements of opinion or critique within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     legen
    -0.54
     dag
    -0.54
     cita
    -0.52
    👈
    -0.52
    ซ์
    -0.51
     dobro
    -0.50
     pop
    -0.47
     ora
    -0.47
     fin
    -0.47
    чан
    -0.47
    POSITIVE LOGITS
    tvguidetime
    1.04
    دانشنامهٔ
    0.92
    SpringRunner
    0.92
     itſelf
    0.91
     MainAxisSize
    0.86
     تضيفلها
    0.85
    Tikang
    0.83
     defaultstate
    0.83
     يتيمه
    0.82
    ungsbedingungen
    0.81
    Act Density 0.191%

    No Known Activations