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

    Neuronpedia

    INDEX
    Explanations

    phrases where someone is requesting or receiving something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "me" and variations of "us" within context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amiya
    -0.74
    eness
    -0.71
    ami
    -0.70
    _.
    -0.67
    Charg
    -0.66
    charg
    -0.64
    Upload
    -0.63
    taboola
    -0.61
    fig
    -0.61
    bell
    -0.57
    POSITIVE LOGITS
    ãģ¦
    0.81
    rov
    0.79
     pause
    0.75
     ample
    0.75
     access
    0.71
     assurances
    0.69
    çīĪ
    0.69
    ãģŁ
    0.68
     abundantly
    0.68
     insight
    0.66
    Act Density 0.079%

    No Known Activations