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

    Neuronpedia

    INDEX
    Explanations

    words related to continuity or things that continue

    oai_token-act-pair · gpt-3.5-turbo

    passive verbs, particularly those related to loss or depletion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     umbrella
    -0.63
     Cambridge
    -0.62
     harvest
    -0.60
     Random
    -0.60
     childbirth
    -0.60
     Giants
    -0.59
     patriot
    -0.59
     potato
    -0.58
     admin
    -0.58
     guys
    -0.57
    POSITIVE LOGITS
    ued
    4.81
    uing
    3.22
    ues
    2.83
    ue
    2.03
    uers
    2.01
    UE
    1.96
    uer
    1.77
    UES
    1.68
    ueless
    1.50
    uable
    1.48
    Act Density 0.006%

    No Known Activations