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

    Neuronpedia

    INDEX
    Explanations

    words related to personal experiences and actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of experiences and accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Axis
    -0.67
     Commodore
    -0.63
    States
    -0.62
    vals
    -0.62
    Britain
    -0.61
     Wiley
    -0.61
    Analysis
    -0.60
     Winston
    -0.59
     Allied
    -0.59
    root
    -0.58
    POSITIVE LOGITS
    ãĤ¦ãĤ¹
    0.73
    cedented
    0.72
    atars
    0.71
     doi
    0.68
     deleted
    0.68
    =""
    0.67
     (@
    0.65
    ttes
    0.63
    ãĤ¼ãĤ¦ãĤ¹
    0.63
     tears
    0.63
    Act Density 0.085%

    No Known Activations