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

    Neuronpedia

    INDEX
    Explanations

    words related to being indivisible or strongly linked

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concepts of visibility and invisibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CLSID
    -0.86
    anooga
    -0.80
    udeb
    -0.78
    MAP
    -0.77
    soDeliveryDate
    -0.73
    IVERS
    -0.72
    WH
    -0.69
    annis
    -0.69
    tu
    -0.69
    iversary
    -0.69
    POSITIVE LOGITS
    adoes
    0.85
     monog
    0.81
    theless
    0.80
     link
    0.68
     hinge
    0.67
     fibre
    0.66
    uable
    0.66
     dom
    0.65
    entity
    0.65
     Tyrann
    0.64
    Act Density 0.102%

    No Known Activations