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

    Neuronpedia

    INDEX
    Explanations

    We're missing the crucial parts for analysis

    oai_token-act-pair · gpt-3.5-turbo

    expressions of dramatic or severe situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appoint
    -0.74
     extrad
    -0.71
     renegoti
    -0.71
     allied
    -0.69
    ulkan
    -0.69
     retaliate
    -0.67
     orchestr
    -0.67
     endeavour
    -0.66
     treasury
    -0.66
     allies
    -0.65
    POSITIVE LOGITS
    Advertisement
    1.15
    SPONSORED
    1.08
    PHOTOS
    0.99
    Suddenly
    0.97
    RELATED
    0.97
    Around
    0.97
    Writing
    0.96
    Newsletter
    0.96
    Eventually
    0.96
    Then
    0.93
    Act Density 1.327%

    No Known Activations