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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a state of being or status related to location or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unggulan
    -0.66
     ambao
    -0.63
     ſhall
    -0.63
    田市
    -0.62
    jalá
    -0.62
     préfère
    -0.61
     Applicability
    -0.60
     <<<<<<<<<<<<<<
    -0.59
    Stylish
    -0.59
     Chriſt
    -0.58
    POSITIVE LOGITS
     ready
    0.76
    par
    0.74
     done
    0.74
     Par
    0.66
     going
    0.62
     GenerationType
    0.62
     تضيفلها
    0.62
     very
    0.62
     seen
    0.60
     reached
    0.60
    Act Density 0.251%

    No Known Activations