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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and linking verbs indicating relationships or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -1.02
     Theſe
    -1.02
     Monfieur
    -1.01
     myſelf
    -0.97
     Conſ
    -0.95
     houſe
    -0.95
     himſelf
    -0.93
     Houſe
    -0.93
    AnimationsModule
    -0.92
     purpoſe
    -0.90
    POSITIVE LOGITS
     usaha
    0.53
    Danh
    0.51
    <tr>
    0.48
     easier
    0.47
     rare
    0.46
     possible
    0.45
     natural
    0.45
    tellung
    0.43
     clear
    0.43
    file
    0.42
    Act Density 0.236%

    No Known Activations