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

    Neuronpedia

    INDEX
    Explanations

    references to people or entities in a list form

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their relationships within a group context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERTISEMENT
    -0.79
    :(
    -0.76
     instead
    -0.64
     wherein
    -0.62
    Enabled
    -0.61
     Feature
    -0.61
    NetMessage
    -0.60
    *
    -0.60
     unden
    -0.59
    *,
    -0.59
    POSITIVE LOGITS
     others
    0.94
     allies
    0.77
    axter
    0.73
     friends
    0.71
     colleagues
    0.68
    friends
    0.67
    ĪĴ
    0.66
     rest
    0.65
     mates
    0.64
     cohorts
    0.64
    Act Density 0.255%

    No Known Activations