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

    Neuronpedia

    INDEX
    Explanations

    sentences that end with a period

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or geographical names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aido
    -0.83
    umbledore
    -0.75
    ccoli
    -0.71
     Hatt
    -0.71
    auga
    -0.70
    gae
    -0.68
    oÄŁan
    -0.67
    opot
    -0.66
    ascus
    -0.66
    anuts
    -0.65
    POSITIVE LOGITS
     V
    2.37
    V
    2.17
    VL
    1.62
     v
    1.61
    VD
    1.60
    v
    1.59
     Vit
    1.54
    Vs
    1.51
    VA
    1.50
     Vet
    1.49
    Act Density 0.490%

    No Known Activations