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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a change in circumstances or perspective

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol represented by "Ļ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.64
     overload
    -0.62
     contrace
    -0.62
     Palestin
    -0.62
     elim
    -0.62
     circulation
    -0.61
     sacrific
    -0.61
     succession
    -0.60
    ammy
    -0.60
     disadvant
    -0.60
    POSITIVE LOGITS
    ï¸ı
    0.89
    ï¸
    0.87
    vana
    0.79
    audi
    0.77
    eal
    0.74
    ski
    0.73
    £
    0.73
    conom
    0.73
    surv
    0.73
    âĤ¬
    0.72
    Act Density 0.305%

    No Known Activations