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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate location or position

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    wpi
    -0.48
     CLIP
    -0.47
    ValueStyle
    -0.45
    NgModule
    -0.45
     householder
    -0.45
     disque
    -0.44
    中断
    -0.44
    ChildScrollView
    -0.44
    OfWork
    -0.44
    diciones
    -0.44
    POSITIVE LOGITS
     assigned
    0.73
    assigned
    0.65
     TextAlign
    0.63
    Personensuche
    0.61
     Assigned
    0.61
     assignment
    0.60
     allocation
    0.60
     allocated
    0.60
     allocations
    0.59
     beginnetje
    0.58
    Act Density 0.119%

    No Known Activations