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

    Neuronpedia

    INDEX
    Explanations

    question phrases containing self-referential language

    oai_token-act-pair · gpt-3.5-turbo

    reflections on self-inquiry and personal questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pour
    -0.83
    bol
    -0.74
    resa
    -0.69
     Sale
    -0.68
    asia
    -0.65
    anche
    -0.63
    icio
    -0.63
    edia
    -0.63
    ubb
    -0.62
    ina
    -0.61
    POSITIVE LOGITS
    ħĭ
    0.90
    çīĪ
    0.81
    selves
    0.80
     exha
    0.77
    åĤ
    0.77
     creatively
    0.74
     è£ıè
    0.72
     nostalg
    0.70
     indec
    0.68
     mate
    0.68
    Act Density 0.031%

    No Known Activations