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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making or introspection

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eree
    -0.53
    natureconservancy
    -0.52
    onymous
    -0.51
    oplan
    -0.51
     utterly
    -0.50
    Lens
    -0.50
    ographically
    -0.50
    RGB
    -0.48
    azing
    -0.48
    virt
    -0.47
    POSITIVE LOGITS
     Ago
    0.67
     ago
    0.64
     yesterday
    0.63
    nesday
    0.62
     bc
    0.62
     confir
    0.59
     indicating
    0.58
     Asked
    0.56
     towards
    0.56
     inquired
    0.55
    Act Density 1.065%

    No Known Activations