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

    Neuronpedia

    INDEX
    Explanations

    verbs related to communication and interaction

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal experiences and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯
    -0.62
     dissip
    -0.61
    Known
    -0.61
    bies
    -0.60
    houses
    -0.60
    ween
    -0.58
    casts
    -0.57
    Ø©
    -0.57
     Plaint
    -0.56
    Pres
    -0.56
    POSITIVE LOGITS
     myself
    1.16
     my
    0.84
    eah
    0.80
    displayText
    0.72
     fortunate
    0.71
     browsing
    0.70
     wondering
    0.70
     personally
    0.69
     researching
    0.68
    EStream
    0.67
    Act Density 0.279%

    No Known Activations