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

    Neuronpedia

    INDEX
    Explanations

    phrases related to aspirations and values

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social issues and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppa
    -0.55
     limb
    -0.55
     snaps
    -0.54
     Volunte
    -0.54
    eb
    -0.53
    database
    -0.53
    iken
    -0.52
    pm
    -0.52
    iff
    -0.51
     Pastebin
    -0.51
    POSITIVE LOGITS
    ynchronous
    0.67
    cum
    0.62
    within
    0.60
    WithNo
    0.60
     embodied
    0.58
    arently
    0.58
     whose
    0.58
    otten
    0.57
     nonetheless
    0.57
    comed
    0.57
    Act Density 0.419%

    No Known Activations