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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate dependency or conditions based on varying factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.71
     tartalomajánló
    -0.62
     <=",
    -0.56
    nyata
    -0.55
     untitled
    -0.55
     sinon
    -0.53
    devamını
    -0.52
    iania
    -0.52
    named
    -0.51
    illées
    -0.50
    POSITIVE LOGITS
     circumstances
    1.02
     type
    0.90
     complexity
    0.88
     severity
    0.87
     circumstance
    0.87
     situation
    0.83
     age
    0.83
     circonstances
    0.81
     season
    0.80
     individual
    0.77
    Act Density 0.609%

    No Known Activations