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

    Neuronpedia

    INDEX
    Explanations

    conditional words and expressions that describe modalities or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fromnode
    -0.82
    ItemBackground
    -0.78
    buttonShape
    -0.72
    zbęd
    -0.71
    ❮
    -0.70
     keskus
    -0.68
    VIAF
    -0.67
     pleaſure
    -0.67
     desselben
    -0.66
     متعلقه
    -0.66
    POSITIVE LOGITS
     auch
    0.67
     schon
    0.63
     ook
    0.56
    reportWebVitals
    0.56
     nicht
    0.55
     csak
    0.55
     noch
    0.53
    deauna
    0.53
     только
    0.53
    bono
    0.51
    Act Density 0.136%

    No Known Activations