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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    names of artists or musicians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ],"
    -0.65
    interstitial
    -0.64
    OWER
    -0.54
    ãģĨ
    -0.53
    à©
    -0.53
    اÙĦ
    -0.52
    taboola
    -0.52
    ibaba
    -0.52
    edom
    -0.51
     liking
    -0.50
    POSITIVE LOGITS
     meanwhile
    1.03
     however
    0.83
     ---------
    0.70
     likewise
    0.69
     agrees
    0.62
     assures
    0.62
     therefore
    0.61
     disagrees
    0.60
     approves
    0.60
     refers
    0.60
    Act Density 1.126%

    No Known Activations