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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating duration or requirements related to agreements or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     automne
    -0.26
     email
    -0.25
     turn
    -0.25
    package
    -0.25
     accueil
    -0.25
     горе
    -0.25
     street
    -0.25
    ثر
    -0.24
    rxjs
    -0.24
     surpresa
    -0.24
    POSITIVE LOGITS
     propOrder
    0.81
     solange
    0.77
     noDo
    0.73
     يتيمه
    0.71
     ſeinen
    0.69
    <unused1>
    0.69
    transQ
    0.69
    <unused43>
    0.69
     MainAxisSize
    0.69
    <unused17>
    0.68
    Act Density 0.194%

    No Known Activations