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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions taken or experiences had

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating expectations or past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    States
    -0.70
    Britain
    -0.69
    nick
    -0.66
    behind
    -0.64
     Julius
    -0.60
    Present
    -0.60
    Eastern
    -0.59
    Roman
    -0.58
    Picture
    -0.57
    Russ
    -0.57
    POSITIVE LOGITS
    ãĥĨ
    0.72
    wcsstore
    0.69
    rontal
    0.69
    °
    0.67
     Been
    0.65
    ãĤ¦ãĤ¹
    0.65
    %:
    0.61
    CLASSIFIED
    0.61
    ansson
    0.59
     plenty
    0.59
    Act Density 0.097%

    No Known Activations