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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intent or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tarko
    -0.42
    httphttps
    -0.41
     HasFactory
    -0.41
     Houſe
    -0.40
     habido
    -0.40
     bluzka
    -0.40
     requirements
    -0.39
     eſſ
    -0.39
     puestos
    -0.38
     soudain
    -0.38
    POSITIVE LOGITS
    OGND
    0.64
     μην
    0.59
    bbean
    0.57
     Италијани
    0.54
     gắng
    0.53
    很想
    0.52
    ussure
    0.52
     να
    0.52
     Administrativna
    0.51
    ⟬
    0.51
    Act Density 0.870%

    No Known Activations