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

    Neuronpedia

    INDEX
    Explanations

    words related to sharing or belonging to a common entity or space

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize shared experiences or collective attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paio
    -0.75
    ª
    -0.71
    ij
    -0.68
    Ł
    -0.66
    ¯
    -0.66
    ľ
    -0.65
    ¿½
    -0.64
     submar
    -0.63
    lems
    -0.63
    ¨
    -0.62
    POSITIVE LOGITS
    edin
    0.94
     secrets
    0.84
    iq
    0.77
     spo
    0.71
     anecdote
    0.70
    onym
    0.69
    oard
    0.69
     workspace
    0.69
     platform
    0.68
     responsibilities
    0.68
    Act Density 0.131%

    No Known Activations