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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific entity or topic, possibly related to news, events, or a particular subject such as "Aggie."

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific group (Aggies) or individuals associated with that group in a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    代
    -0.81
    çīĪ
    -0.76
    ãĤ´ãĥ³
    -0.69
    neck
    -0.68
    YP
    -0.68
    PIN
    -0.65
    ãĥķãĤ©
    -0.65
    éļ
    -0.62
    ï¸ı
    -0.60
    HCR
    -0.60
    POSITIVE LOGITS
    regate
    1.23
    ressive
    0.93
    ressor
    0.90
    Agg
    0.89
    ements
    0.85
    -+-+
    0.85
    esville
    0.82
    enn
    0.81
    eties
    0.79
    ---------------
    0.79
    Act Density 0.031%

    No Known Activations